WO2023090758A1 - 음파 신호를 이용하여 노면 종류를 추정하고 관리하는 장치 및 그 방법 - Google Patents
음파 신호를 이용하여 노면 종류를 추정하고 관리하는 장치 및 그 방법 Download PDFInfo
- Publication number
- WO2023090758A1 WO2023090758A1 PCT/KR2022/017680 KR2022017680W WO2023090758A1 WO 2023090758 A1 WO2023090758 A1 WO 2023090758A1 KR 2022017680 W KR2022017680 W KR 2022017680W WO 2023090758 A1 WO2023090758 A1 WO 2023090758A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- road surface
- road
- sound wave
- signal
- present disclosure
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 99
- 238000013528 artificial neural network Methods 0.000 claims description 123
- 230000005540 biological transmission Effects 0.000 claims description 116
- 150000003839 salts Chemical class 0.000 claims description 60
- 239000007921 spray Substances 0.000 claims description 49
- 230000009466 transformation Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 60
- 238000007726 management method Methods 0.000 description 41
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 37
- 238000013145 classification model Methods 0.000 description 35
- 238000012544 monitoring process Methods 0.000 description 32
- 238000012545 processing Methods 0.000 description 29
- 238000004458 analytical method Methods 0.000 description 28
- 230000011218 segmentation Effects 0.000 description 27
- 230000008878 coupling Effects 0.000 description 25
- 238000010168 coupling process Methods 0.000 description 25
- 238000005859 coupling reaction Methods 0.000 description 25
- 230000006870 function Effects 0.000 description 25
- 238000010438 heat treatment Methods 0.000 description 25
- 238000013473 artificial intelligence Methods 0.000 description 24
- 230000008859 change Effects 0.000 description 24
- 238000004891 communication Methods 0.000 description 23
- 230000008569 process Effects 0.000 description 22
- 238000006243 chemical reaction Methods 0.000 description 18
- 238000009434 installation Methods 0.000 description 17
- 238000010276 construction Methods 0.000 description 15
- 238000001514 detection method Methods 0.000 description 14
- 238000012937 correction Methods 0.000 description 13
- 230000000694 effects Effects 0.000 description 13
- 238000005259 measurement Methods 0.000 description 13
- 238000009826 distribution Methods 0.000 description 12
- 238000013527 convolutional neural network Methods 0.000 description 11
- 238000003860 storage Methods 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 10
- 238000002347 injection Methods 0.000 description 10
- 239000007924 injection Substances 0.000 description 10
- 238000003062 neural network model Methods 0.000 description 10
- 238000012706 support-vector machine Methods 0.000 description 10
- 230000001681 protective effect Effects 0.000 description 9
- 239000000463 material Substances 0.000 description 8
- 230000008014 freezing Effects 0.000 description 7
- 238000007710 freezing Methods 0.000 description 7
- 238000010606 normalization Methods 0.000 description 7
- 238000007781 pre-processing Methods 0.000 description 7
- 238000005070 sampling Methods 0.000 description 7
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 6
- 230000008018 melting Effects 0.000 description 6
- 238000002844 melting Methods 0.000 description 6
- 230000002265 prevention Effects 0.000 description 6
- 238000005507 spraying Methods 0.000 description 6
- 230000036961 partial effect Effects 0.000 description 5
- 238000012546 transfer Methods 0.000 description 5
- 239000010426 asphalt Substances 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 229910052757 nitrogen Inorganic materials 0.000 description 3
- 230000000704 physical effect Effects 0.000 description 3
- 101100365516 Mus musculus Psat1 gene Proteins 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000001678 irradiating effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 230000001172 regenerating effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000003746 surface roughness Effects 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 101100370014 Neurospora crassa (strain ATCC 24698 / 74-OR23-1A / CBS 708.71 / DSM 1257 / FGSC 987) tof-1 gene Proteins 0.000 description 1
- 235000009413 Ratibida columnifera Nutrition 0.000 description 1
- 241000510442 Ratibida peduncularis Species 0.000 description 1
- 239000011358 absorbing material Substances 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000002730 additional effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000004579 marble Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
- E01C23/00—Auxiliary devices or arrangements for constructing, repairing, reconditioning, or taking-up road or like surfaces
- E01C23/01—Devices or auxiliary means for setting-out or checking the configuration of new surfacing, e.g. templates, screed or reference line supports; Applications of apparatus for measuring, indicating, or recording the surface configuration of existing surfacing, e.g. profilographs
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B1/00—Nozzles, spray heads or other outlets, with or without auxiliary devices such as valves, heating means
- B05B1/14—Nozzles, spray heads or other outlets, with or without auxiliary devices such as valves, heating means with multiple outlet openings; with strainers in or outside the outlet opening
- B05B1/20—Arrangements of several outlets along elongated bodies, e.g. perforated pipes or troughs, e.g. spray booms; Outlet elements therefor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/08—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means
- B05B12/12—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to conditions of ambient medium or target, e.g. humidity, temperature position or movement of the target relative to the spray apparatus
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B13/00—Machines or plants for applying liquids or other fluent materials to surfaces of objects or other work by spraying, not covered by groups B05B1/00 - B05B11/00
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
- E01C11/00—Details of pavings
- E01C11/24—Methods or arrangements for preventing slipperiness or protecting against influences of the weather
- E01C11/26—Permanently installed heating or blowing devices ; Mounting thereof
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
- E01C11/00—Details of pavings
- E01C11/24—Methods or arrangements for preventing slipperiness or protecting against influences of the weather
- E01C11/26—Permanently installed heating or blowing devices ; Mounting thereof
- E01C11/265—Embedded electrical heating elements ; Mounting thereof
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01F—ADDITIONAL WORK, SUCH AS EQUIPPING ROADS OR THE CONSTRUCTION OF PLATFORMS, HELICOPTER LANDING STAGES, SIGNS, SNOW FENCES, OR THE LIKE
- E01F9/00—Arrangement of road signs or traffic signals; Arrangements for enforcing caution
- E01F9/40—Arrangements responsive to adverse atmospheric conditions, e.g. to signal icy roads or to automatically illuminate in fog; Arrangements characterised by heating or drying means
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01H—STREET CLEANING; CLEANING OF PERMANENT WAYS; CLEANING BEACHES; DISPERSING OR PREVENTING FOG IN GENERAL CLEANING STREET OR RAILWAY FURNITURE OR TUNNEL WALLS
- E01H10/00—Improving gripping of ice-bound or other slippery traffic surfaces, e.g. using gritting or thawing materials ; Roadside storage of gritting or solid thawing materials; Permanently installed devices for applying gritting or thawing materials; Mobile apparatus specially adapted for treating wintry roads by applying liquid, semi-liquid or granular materials
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01H—STREET CLEANING; CLEANING OF PERMANENT WAYS; CLEANING BEACHES; DISPERSING OR PREVENTING FOG IN GENERAL CLEANING STREET OR RAILWAY FURNITURE OR TUNNEL WALLS
- E01H10/00—Improving gripping of ice-bound or other slippery traffic surfaces, e.g. using gritting or thawing materials ; Roadside storage of gritting or solid thawing materials; Permanently installed devices for applying gritting or thawing materials; Mobile apparatus specially adapted for treating wintry roads by applying liquid, semi-liquid or granular materials
- E01H10/005—Permanently-installed devices for applying gritting or thawing materials, e.g. for spreading grit, for spraying de-icing liquids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H3/00—Measuring characteristics of vibrations by using a detector in a fluid
- G01H3/04—Frequency
- G01H3/06—Frequency by electric means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
Definitions
- the present disclosure relates to an apparatus for estimating the type of a road surface using a sound wave signal and a method for classifying and managing a road surface using the same, and more particularly, by classifying a sound wave signal reflected on a road surface using an artificial neural network and classifying the classified A device for controlling a road surface or a moving object based on a type of road surface and a road surface management method using the same.
- ground vehicles moving on the ground perform acceleration and deceleration control according to the friction coefficient of the moving ground, that is, the road surface, so it is important to accurately estimate the road surface friction coefficient in terms of stability control and maximum motion performance control.
- Black ice accidents which are rapidly increasing in winter, are an example of the need for road friction coefficient estimation technology in that they occur due to rapid changes in the road friction coefficient without being aware of it.
- the friction coefficient of the road surface can be remotely estimated, but expensive sensor equipment and a corresponding signal processing device are required for this purpose, and the result depends on the mounting position or direction of the sensor. There are limits to what can change.
- road surface estimation technology using sound information is also actively discussed.
- the focus is on technology for estimating the road surface condition based on the frictional sound between the ground and tires, which not only lacks accuracy but also causes the road surface in front to pass through.
- the state cannot be checked.
- the present disclosure intends to provide an apparatus and method for estimating a type of road surface using a sound wave signal.
- an electronic device for classifying a road surface using sound wave signals includes a transceiver configured to transmit and receive sound wave signals; atmospheric sensor; and at least one processor electronically connected to the transceiver and the atmospheric sensor, wherein the at least one processor transmits a sound wave signal toward a target road spaced apart from the electronic device by a first distance using the transceiver. and receiving a reflected signal of the sound wave signal with respect to the target road surface using the transceiver, obtaining atmospheric information associated with the sound wave signal using the atmospheric sensor, and obtaining a first signal for the received reflected signal.
- Acquiring data generating second data by correcting the first data based on the atmospheric information, and acquiring third data related to frequency domain information of the second data based on the second data, It is set to determine the type of the target road surface based on the third data and a road classification artificial neural network, and the road classification artificial neural network is generated based on a sound wave signal reflected from a road surface at a second distance different from the first distance. can be learned with a frequency domain data set.
- the second data may be generated by correcting the first data based on the waiting information and the first distance.
- the first distance may be estimated based on a transmission time of the sound wave signal and a reception time of the reflected signal.
- the third data may be obtained by short-time Fourier transform (STFT) transform of the second data.
- STFT short-time Fourier transform
- the at least one processor may be configured to generate a signal for controlling a road surface management device installed on the target road surface based on the determined type of the target road surface.
- the road surface management device may include a hot wire or a salt water spray device.
- the at least one processor is configured to determine whether a preset weather condition is satisfied, and to generate a signal for controlling the road surface management device when the preset weather condition is satisfied.
- the at least one processor checks whether the type of the target road surface determined at the first time point is changed at the second time point, and determines whether the first class determined as the type of the target road surface at the first time point and the first When the second class determined as the type of the target road surface at two points in time is different from each other, it is set to determine whether to generate a control signal for a device installed on the target road surface based on the type of the target road surface determined at a third point in time.
- the type of the target road surface is determined every first period, and the at least one processor determines the type of the target road surface when the type of the target road surface is determined to be in the first class. It may be set to be judged every 2 cycles.
- the electronic device further includes at least one of an IR sensor for acquiring temperature information of the target road surface and a vision sensor for acquiring image information of the target road surface, and the at least one processor , It may be set to determine the type of the road surface further based on the temperature information or the image information.
- a method of classifying a road surface using a sound wave signal performed by an electronic device may include transmitting a sound wave signal toward a target road surface separated from the electronic device by a first distance; Receiving a reflected signal of the sound wave signal with respect to the target road surface; acquiring atmospheric information associated with the sound wave signal; obtaining first data for the received reflected signal; generating second data by correcting the first data based on the standby information; obtaining third data related to frequency domain information of the second data based on the second data; and determining the type of the target road surface based on the third data and a road classification artificial neural network, wherein the road classification artificial neural network determines a sound wave signal reflected from a road surface at a second distance different from the first distance. It can be learned with a frequency domain data set generated based on
- the road surface management can be economically and efficiently managed by automatically controlling the road surface management using the classification information of the road surface.
- the present disclosure can provide more effective traffic network information to users by obtaining road surface information in real time.
- FIG. 1 is a block diagram of a road classification device according to various embodiments of the present disclosure.
- FIG. 2 is a diagram illustrating that a road classification device according to an embodiment of the present disclosure is installed and operated in a road infrastructure.
- FIG. 3 is a flowchart illustrating a method performed by a road classification device according to the present disclosure.
- FIG. 4 is a diagram illustrating a sound wave signal transmitted from a road classification device according to various embodiments of the present disclosure on a time axis.
- FIG. 5 is a diagram illustrating a transmission period of a sound wave signal and a reception period of a reflected signal according to an embodiment of the present disclosure.
- FIG. 6 is a diagram illustrating a target on which a road classification device according to various embodiments of the present disclosure is installed.
- FIG. 7 is a diagram illustrating a method of obtaining a data set for learning a road classification artificial neural network according to various embodiments of the present disclosure.
- FIG. 8 is a flowchart illustrating a process of pre-processing a received reflected signal by a road classification apparatus according to various embodiments of the present disclosure.
- FIG. 9 is a diagram illustrating a multi-modal artificial neural network according to an embodiment of the present disclosure.
- FIG. 10 is a flowchart illustrating an operation of changing a control operation based on a predetermined control change trigger by a road surface classification apparatus according to an embodiment of the present disclosure.
- FIG. 11 is a diagram illustrating a scenario in which a road surface classification result is changed according to an embodiment of the present disclosure.
- FIG. 12 is a diagram illustrating a road surface management method by a road classification device according to various embodiments of the present disclosure.
- FIG. 13 is a diagram illustrating that a road classification apparatus according to an embodiment of the present disclosure collects traffic information.
- FIG. 14 is a configuration diagram of a road surface type estimation device according to an embodiment of the present disclosure.
- 15 is a diagram for explaining a transmission signal and a reception signal in an apparatus for estimating a type of road surface using sound waves according to an embodiment of the present disclosure.
- 16 is a diagram for exemplarily explaining a signal converter in an apparatus for estimating a type of road surface using sound waves according to an embodiment of the present disclosure.
- 17 is a diagram for explaining an artificial neural network in an apparatus for estimating a road surface type using sound waves according to an embodiment of the present disclosure.
- 18 is a diagram for explaining the operation of a convolution performer.
- 19 is a diagram for explaining a code of a convolution performer of an apparatus for estimating a road surface type using sound waves according to an exemplary embodiment of the present disclosure.
- 20 is a flowchart of a method for estimating a type of road surface using domain conversion of sound waves according to an embodiment of the present disclosure.
- 21 is a flowchart illustrating an embodiment of a method for estimating a type of road surface using sound waves according to the present disclosure.
- FIG. 22 is a flowchart illustrating a method for estimating a road surface type using sound waves in which atmospheric attenuation is corrected according to an embodiment of the present disclosure.
- FIG. 23 is a diagram for explaining a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- FIG. 24 is a configuration diagram of a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- 25 is a diagram illustratively illustrating recognizing a uniform road surface condition in a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- 26 is a diagram illustratively illustrating recognizing a non-uniform road surface condition in a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- FIG. 27 is a diagram for explaining a method of finding a segmentation area detected by an acoustic wave sensor in a road condition monitoring system equipped with a vision sensor and an acoustic wave sensor according to an embodiment of the present disclosure.
- FIG. 28 is a diagram for explaining an example of an artificial neural network of a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- 29 is a diagram for explaining an example of a segmentation processing unit of a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- FIG. 30 is a flowchart of an embodiment of a monitoring method in a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to the present disclosure.
- FIG. 31 is a detailed flowchart of an embodiment of the fusion analysis step 3050 of FIG. 30 .
- FIG. 32 is a configuration diagram of a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to another embodiment of the present disclosure.
- FIG 33 is a flowchart of another embodiment of a monitoring method in a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to the present disclosure.
- 34 is a diagram for explaining an operation of a control system of a heating wire system for a road according to an embodiment of the present disclosure.
- 35 is a block diagram of a control system of an apparatus for preventing icing on a road according to an embodiment of the present disclosure.
- 36 is a block diagram of a control system of an apparatus for preventing icing on a road according to another embodiment of the present disclosure.
- 37A to 37C are diagrams for explaining an artificial intelligence analysis model used in a control system of an apparatus for preventing icing on a road according to an embodiment of the present disclosure.
- 38 is a flowchart of a control method of an apparatus for preventing icing on a road according to an embodiment of the present disclosure.
- FIG. 39 is a detailed flowchart of one embodiment of the control signal generation step 3850 of FIG. 38 when the device for preventing icing on a road according to the present disclosure is a hot wire device.
- FIG. 40 is a detailed flowchart of one embodiment of the control signal generation step 3850 of FIG. 38 when the device for preventing icing on a road according to the present disclosure is a salt water spray device.
- 41 is a perspective view schematically illustrating a road infrastructure sensor construction structure according to an embodiment of the present disclosure.
- FIG. 42 is a side view schematically illustrating a road infrastructure sensor construction structure according to an embodiment of the present disclosure.
- FIG 43 is a perspective view (a) and a partial cross-sectional perspective view (b) schematically illustrating an acoustic wave sensor unit according to an embodiment of the present disclosure.
- FIG 44 is a partial side cross-sectional view schematically illustrating a sound wave sensor unit according to an embodiment of the present disclosure.
- 45 is a perspective view schematically illustrating a road infrastructure sensor construction structure according to another embodiment of the present disclosure.
- 46 is a side view schematically illustrating a road infrastructure sensor construction structure according to another embodiment of the present disclosure.
- FIG 47 is a partially enlarged perspective view (a), a bottom perspective view (b), and a partial cross-sectional perspective view (b) schematically showing a road infrastructure sensor construction structure according to another embodiment of the present disclosure.
- FIG. 48 is a partial side cross-sectional view schematically illustrating a sound wave sensor unit according to another embodiment of the present disclosure.
- 49 is a flowchart illustrating a construction method of a road infrastructure sensor construction structure according to a preferred embodiment of the present disclosure.
- first and/or “second” may be used to describe various components, but the components should not be limited by the terms. The above terms are only for the purpose of distinguishing one component from another component, e.g., without departing from the scope of rights according to the concept of the present disclosure, a first component may be termed a second component, and similarly The second component may also be referred to as the first component.
- each block of the process flow diagrams and combinations of the flow diagrams may be performed by computer program instructions.
- These computer program instructions may be embodied in a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment are described in the flowchart block(s). It creates means to perform functions.
- These computer program instructions may also be stored in a computer usable or computer readable memory that can be directed to a computer or other programmable data processing equipment to implement functionality in a particular way, such that the computer usable or computer readable memory
- the instructions stored in may also be capable of producing an article of manufacture containing instruction means that perform the functions described in the flowchart block(s).
- the computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to generate computer or other programmable data processing equipment. Instructions for performing the processing equipment may also provide steps for performing the functions described in the flowchart block(s).
- each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). It should also be noted that in some alternative implementations it is possible for the functions mentioned in the blocks to occur out of order. For example, two blocks shown in succession may in fact be executed substantially concurrently, or the blocks may sometimes be executed in reverse order depending on their function.
- 'unit' used in the present disclosure refers to software or a hardware component such as a Field Programmable Gate Array (FPGA) or Application Specific Integrated Circuit (ASIC).
- FPGA Field Programmable Gate Array
- ASIC Application Specific Integrated Circuit
- ' ⁇ Part' performs specific roles, but is not limited to software or hardware.
- ' ⁇ bu' may be configured to be in an addressable storage medium and may be configured to reproduce one or more processors.
- ' ⁇ unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and programs. procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.
- components and ' ⁇ units' may be combined into smaller numbers of components and ' ⁇ units' or further separated into additional components and ' ⁇ units'.
- components and ' ⁇ units' may be implemented to play one or more CPUs in a device or a secure multimedia card.
- ' ⁇ unit' may include one or more processors.
- the present disclosure relates to a system for classifying a road surface using a sound wave signal and managing the road surface or vehicle operation through the classification.
- a road surface classification device may include a device installed on a road infrastructure or a mobile body to determine the type or condition of a road surface.
- a road surface classification apparatus may include a server device that determines the type or state of a road surface based on information received from a device installed in a road infrastructure or a moving object.
- FIG. 1 is a block diagram of a road classification device according to various embodiments of the present disclosure.
- a road classification apparatus 100 may include a transceiver 110 , a sensing unit 120 , and a control unit 130 .
- the road classification device may include additional components in addition to the hardware components described above, and is not limited to the components shown in FIG. 1 .
- 1 is for illustrating hardware components constituting the road classification device 100 of the present disclosure, and the road classification device according to another embodiment of the present disclosure is configured by omitting some of the components shown in FIG. It can be.
- the transceiver 110 is a hardware component configured to transmit and receive sound wave signals, and may include a transmitter (not shown) and a receiver (not shown) or a transceiver (not shown).
- a transmitter not shown
- a receiver not shown
- a transceiver not shown
- the transmitter is a device that generates and transmits a sound wave signal, and may be disposed in a direction in which the sound wave signal is emitted toward a road surface. At this time, the emitted sound wave signal may include a high-frequency ultrasonic signal.
- the frequency of the generated sound wave signal may be fixed according to the type of transmitter, or set by a user input or may be variable.
- the sound wave signal may be transmitted singly according to a user input, control of a controller or server, or a predetermined rule, or one or a plurality of signals may be periodically transmitted during one period. In this case, the number of transmitted sound waves or transmission period may be variable.
- the receiver is a device for receiving a sound wave signal, and may be arranged to receive a sound wave signal reflected from a road surface.
- the receiver may directly receive a sound wave signal transmitted from an adjacent transmitter in addition to the reflected signal. Since the signal directly received from the transmitter is a signal irrelevant to the classification of the road to be determined by the road classification device of the present disclosure, it can be regarded as noise, and such a noise signal is called cross-talk.
- a transmitter and a receiver may be installed apart from each other in order to reduce crosstalk.
- a structure such as a sound absorbing material or a sound insulating material is additionally provided between the transmitter and the receiver. can be placed.
- the structure may be formed of a material or structure having physical properties of attenuating or absorbing sound waves, and may be an electronic device configured to implement such physical properties.
- a transceiver is a term including a transmitter, a receiver, or both transceivers, and a transceiver may mean a hardware device in which a transmitter and a receiver are integrated into one, including both physically separated transmitters and receivers, or each of them. It can also mean referring to.
- the transceiver may transmit or receive sound waves within an angle of view range according to hardware performance.
- the road classification device 100 may use transceivers having different beam angles in consideration of a target or environment in which the road classification device is installed. For example, a beam angle of a transceiver used in a road classification device disposed in a road infrastructure may be smaller than a beam angle of a transceiver used in a road classification device installed in a vehicle.
- the transmitter and the receiver may be disposed in consideration of a mutual beam angle.
- the receiver according to an embodiment of the present disclosure may be disposed outside the beam angle range of the transmitter, and through this, the outermost sound wave signal of the beam angle emitted from the transmitter may not be detected by the receiver.
- a receiver according to another embodiment of the present disclosure may be disposed on an outer side with respect to the center of the beam angle of the transmitter so that a crosstalk signal detected by the receiver is less than or equal to a reference value.
- a transceiver may be designed or arranged to respond only to a specific frequency characteristic of a reflected wave with respect to a road surface.
- the sensing unit 120 is a hardware component that obtains information necessary for road surface classification according to the present disclosure through measurement, and the sensing unit 120 according to the present disclosure may include an air sensor, a camera, and/or an IR sensor. .
- the sensing unit 120 may include a standby sensor.
- the air sensor is a hardware device that obtains information related to an air state, and the air information measured or obtained by the air sensor may include at least one of temperature, humidity, or air pressure.
- the atmospheric information may further include wind information.
- the wind information may include a physical quantity related to the wind, such as wind speed, wind volume, or wind direction.
- an atmospheric sensor may refer to a device including at least one of a temperature sensor, a humidity sensor, and an air pressure sensor.
- the air sensor may mean a device capable of sensing a plurality of different air information.
- the atmospheric sensor according to an embodiment of the present disclosure may measure temperature, humidity, air pressure, and/or wind speed of a place where the road classification device is located.
- the sensing unit 120 may further include a camera and/or an IR sensor.
- the camera is a device for acquiring images and may obtain image information on the road surface
- the IR sensor may obtain temperature information of the road surface by detecting radiant heat emitted from the road surface. Since the temperature information acquired by the IR sensor is temperature information about the road surface and the temperature information obtained by the air sensor is temperature information about the air, the values indicated by the respective temperature information acquired by different sensors may be different. .
- the road classification result output by the road classification apparatus 100 may be generated based on a plurality of pieces of information, and specific embodiments thereof will be described later.
- the camera and/or IR sensor included in the sensing unit 120 is exemplary, and the sensing unit 120 is used to classify the road surface in addition to the atmospheric sensor, camera, or IR sensor described above. Any sensing device that obtains possible information may be further included.
- the control unit 130 is hardware set to perform the method performed by the road classification device of the present disclosure, and may include at least one processor including a logic circuit and an arithmetic circuit.
- the controller 130 may process data according to a program and/or instructions provided from a memory (not shown), and may generate a control signal according to a processing result.
- the controller 130 may control at least one other component (eg, hardware or software component) of the road classification device 100 connected to the controller 130, It can perform various data processing or calculations.
- the control unit 130 stores commands or data received from other components (eg, the receiver 120 or the sensing unit 120) in a volatile memory (not shown). , processing commands or data stored in a volatile memory (not shown), and storing resultant data in a non-volatile memory (not shown).
- a signal obtained through the receiver 120 may be converted into a digital signal and processed through an analog to digital converter (ADC) circuit included in the control unit 130 .
- ADC analog to digital converter
- the converted digital signal may be pre-processed as input data for input to an artificial neural network.
- control unit 130 may include a main processor (eg, a central processing unit (CPU) or an application processor (AP)) or an auxiliary processor (eg, a graphic processing unit (GPU)) operable independently of or together with the main processor, a neural network It may include a processing unit (NPU: neural processing unit), an image signal processor, a sensor hub processor, or a communication processor).
- a main processor e.g, a central processing unit (CPU) or an application processor (AP)
- auxiliary processor eg, a graphic processing unit (GPU)
- the auxiliary processor may use less power than the main processor or may be set to be specialized for a designated function.
- a secondary processor may be implemented separately from, or as part of, the main processor.
- the road classification device may include a communication unit (not shown).
- the communication unit receives a command or data input from a user or other external device, transmits a command or data generated by the road classification device to the outside, or transmits a command or data from other component(s) of the road classification device.
- it refers to a receiving hardware component, and may include a wired/wireless communication module and/or an input/output interface.
- the road classification device receives information from an external electronic device (eg, a control box or a management server installed outside the road classification device) through the communication unit, or the external electronic device The information obtained or generated by the road classification device may be transmitted.
- the communication unit may be implemented separately from the control unit 130 in the road classification device according to various embodiments of the present disclosure, and may be implemented through circuit elements included in the control unit 130 and included in the control unit 130.
- the road classification device may be a device that provides information necessary for classifying a road surface in conjunction with an external electronic device.
- the artificial neural network (not shown) for classifying the road surface of the present disclosure is included in the controller 130 as a software-on-chip (SOC) or a micro controller unit (MCU) in the road classification device.
- SOC software-on-chip
- MCU micro controller unit
- the artificial neural network may be provided in the form of software operated by the controller 130 and updated by communication from an external server or user input.
- the artificial neural network may be implemented in an external electronic device (eg, the controller or the server), and in this case, the controller 130 of the road classification device generates the artificial neural network based on the sound wave signal.
- Data required for road classification such as road surface classification data and standby information, is transmitted to an external electronic device, and the external electronic device can classify the road surface based on the data received from the road classification device.
- the road classification device may be a server device.
- the road classification device may not include the sound wave transceiver 110 and the sensing unit 120, receives data necessary for road classification from an external electronic device through a communication unit (not shown), and transmits data to the received data. Based on this, the controller 130 may classify the road surface. In addition, a classified road surface classification result and/or related control information may be transmitted to an external electronic device.
- FIG. 2 is a diagram illustrating that a road classification device according to an embodiment of the present disclosure is installed and operated in a road infrastructure.
- the road surface classification device 100 may be installed to face a road surface 230 to be classified in the road infrastructure 200 .
- the road infrastructure 200 is a term that collectively refers to traffic facilities including support-type structures 210 such as traffic lights, street lights, road guide signs, or image information processing devices installed on or along the road. It refers to a structure on which a road classification device can be installed, and is not limited to the above example. According to one embodiment of the present disclosure, the installation of the road surface classification device 100 in the road infrastructure 200 may mean installation at the upper end of the post-type structure 210, but is not limited thereto.
- the road infrastructure 200 may include a controller 220 for controlling electronic devices installed on the pillar-type structure 210 .
- the electronic device installed on the pillar-type structure 210 may include a light emitting device used for streetlights or traffic lights, a CCTV, a traffic information collection camera, or a road classification device according to the present disclosure.
- the controller 220 is a device for controlling electronic devices installed in the holding-type structure 210.
- the holding-type structure is a street light
- it may be a street light controller that controls the operation of the street light
- the holding-type structure In the case of traffic lights, it may be a traffic signal controller that controls signals of traffic lights.
- the controller 220 may control the operation of the road classification device 100 of the present disclosure, and road infrastructure ( 200) can be controlled.
- the controller 220 may serve as a gateway between the road classification device 100 and a management server (not shown). That is, the controller 220 may include a wired/wireless communication module, transmit information obtained from the road classification device to the management server, or receive commands or data for controlling the road classification device or road from the management server. .
- the controller 220 may include the artificial neural network of the present disclosure, and through this, may directly classify a road surface based on information obtained from a road classification device.
- the artificial neural network provided to the controller 220 is provided to the road classification device 100. It can outperform artificial neural networks.
- the controller 220 may control the road surface management device 250 installed on the road based on the classified road surface to manage the road surface.
- the road surface management device 250 may include a snow removal device such as a heat wire or a salt water spray device installed on a road, or a drainage facility. Details of operation of the road surface management device according to various embodiments of the present disclosure will be described later.
- a snow removal device such as a heat wire or a salt water spray device installed on a road, or a drainage facility. Details of operation of the road surface management device according to various embodiments of the present disclosure will be described later.
- a reflected signal for the same sound wave incident signal is different for each material. Therefore, materials can be distinguished by analyzing the reflected signal using these physical characteristics.
- acoustic impedance is a physical quantity having frequency characteristics, the material of the reflecting surface can be classified more precisely by analyzing the reflected signal in the frequency domain.
- An artificial neural network may be used to perform a road surface classification method using a sound wave reflection signal according to various embodiments of the present disclosure.
- a neural network model of an artificial neural network may include a plurality of layers or layers.
- the neural network model may be implemented in the form of a classifier generating road surface classification information.
- a classifier can perform multiple classifications.
- the neural network model may be a multi-classification model that classifies results of input data into a plurality of classes.
- a neural network model may include a deep neural network (DNN) of a multi-layer perceptron algorithm including an input layer, a plurality of hidden layers, and an output layer.
- DNN deep neural network
- a neural network model according to another embodiment of the present disclosure may include a Convolutional Neural Network (CNN).
- CNN Convolutional Neural Network
- a neural network model may be implemented to include a plurality of VGGNet blocks.
- the neural network model includes a first structure in which a CNN layer having 64 filters in a 3x3 size, a Batch Normalization (BN) layer, and a ReLU layer are sequentially combined, a CNN layer having 128 filters in a 3x3 size, a ReLU layer, and A second block in which BN layers are sequentially combined may be prepared by combining.
- the neural network model includes a max pooling layer following each CNN block, and may include a global average pooling (GAP) layer, a fully connected (FC) layer, and an activation layer (eg, sigmoid, softmax, etc.) at the end. there is.
- GAP global average pooling
- FC fully connected
- activation layer eg, sigmoid, softmax, etc.
- An artificial neural network refers to a neural network model for classifying a road surface by extracting characteristics from a frequency conversion signal of a sound wave signal, and is not limited to the above example.
- the road classification artificial neural network may be trained using the frequency domain data of the reflected signal as an input value, and the learned artificial neural network may be trained using the frequency domain data of the target signal as an input value.
- the surface can be classified.
- the frequency domain data may refer to data obtained by performing frequency domain conversion on a digital signal converted through ADC sampling of a reflected signal.
- Short-Time Fourier Transform (STFT) transform As a frequency domain transform method according to various embodiments of the present disclosure, Short-Time Fourier Transform (STFT) transform, Fast Fourier Transform (FFT) transform, cepstrum transform, wavelet transform, and cross-correlation method , convolution transformation, etc. may be used.
- STFT Short-Time Fourier Transform
- FFT Fast Fourier Transform
- cepstrum transform cepstrum transform
- wavelet transform wavelet transform
- cross-correlation method convolution transformation, etc.
- convolution transformation etc.
- the above-described frequency domain conversion method is illustrative, and is not limited to the listed conversion methods, and various conversion or analysis methods for analyzing a sound wave signal in the time domain in the frequency domain may be used.
- spectrogram data obtained through STFT transformation may be included.
- frequency domain data may include data obtained by applying a cross-correlation method.
- the cross-correlation synthesis of the input data can correspond to the step of inputting the data to the convolution layer, CNN-based learning and classification can be possible using this.
- the frequency domain data used for learning may be labeled along with information necessary for road classification.
- the labeled information may include the type of road surface and/or standby information.
- the learning data set may include a data set in which the type of road surface from which each data was obtained is labeled in frequency domain data.
- the types (classes) of the road surface classified by the road surface classification device include asphalt, cement, soil, ice, marble, paint, slush (a mixture of water and ice), snow, and water. It may contain classes such as The types of listed classes are exemplary, and the number or groups of classes to be classified may vary according to circumstances in various embodiments of the present disclosure. Meanwhile, instead of using such a direct labeling method or group name, each input data may be grouped in an arbitrary method such as the first class and the second class. Grouping in this arbitrary method may be a classification result in the case of using an unsupervised artificial neural network in which a label is not included in training data, but is not limited thereto.
- FIG. 3 is a flowchart illustrating a method performed by a road classification device according to the present disclosure. According to various embodiments, the operations shown in FIG. 3 may be performed in various orders without being limited to the order shown. Also, according to various embodiments, more operations than the operations shown in FIG. 3 or at least one operation less may be performed. 4 to 12 may be referred to as drawings for further explanation of the operations shown in FIG. 3 .
- the road classification apparatus may transmit or emit a sound wave signal toward the classification target road surface using a transmitter.
- the sound wave signal may be transmitted at least once, and the frequency or transmission period of the signal may be changed according to a user's input, preset conditions, or server control.
- the sound wave signal is transmitted multiple times within one determination period, since a plurality of data for determining the classification or state of the road surface can be acquired, the accuracy of the road classification can be improved.
- a specific embodiment of a period of transmitting sound wave signals and an operation of transmitting multiple times within one period will be described later with reference to FIG. 4 .
- the road classification apparatus may receive a signal reflected from the target road surface using a receiver. Since the reflected signal is a reflected signal for the transmitted sound wave signal, the sound wave signal and the reflected signal may correspond to each other. When a plurality of sound wave signals are transmitted, reflection signals corresponding thereto may be received a plurality of times.
- the road classification apparatus may obtain atmospheric information through an atmospheric sensor of the sensing unit 120 when a sound wave signal is transmitted.
- the time point at which air information is acquired does not necessarily coincide with the time point at which the sound wave signal is transmitted, and it means that there exists a correspondence with each other within a certain time interval. That is, the road classification apparatus may acquire air information corresponding to one sound wave signal or air information corresponding to a plurality of sound wave signals.
- the road classification apparatus may process a reflected signal corresponding to a sound wave signal based on atmospheric information corresponding to a emitted sound wave signal.
- the time from when one sound wave signal is transmitted from the transmitter to when the reflected signal is received by the receiver after being reflected by the road surface may be defined as time of flight (ToF). Since the propagation speed of sound waves in the air can be determined under specific weather conditions, the distance between the road classification device and the target road surface can be measured based on ToF and atmospheric information. Conversely, when the distance between the road classification device and the target road surface is known in advance, ToF may be estimated. Accordingly, the road classification apparatus according to various embodiments of the present disclosure may identify a received signal corresponding to a sound wave signal transmitted from a transmitter.
- a receiving period of a received signal corresponding to a sound wave signal transmitted from a transmitter may be determined, and a signal received in the corresponding time period may be determined as a reflection signal of the transmitted sound wave signal, and signals received in other time periods may be treated as noise. It can be regarded as a reflection signal for other sound wave signals.
- a detailed embodiment of a control method of a road classification device for controlling a noise signal using this will be described later with reference to FIG. 5 .
- the road classification apparatus 100 may pre-process the received reflected signal through the controller to obtain data to be input to the road classification artificial neural network according to the present disclosure.
- signal pre-processing refers to all processes of obtaining data to be input to an artificial neural network based on a received reflected signal
- the pre-processing operation in step 303 includes an operation of sampling an analog signal into a digital signal, It may include signal attenuation correction, ToF correction, frequency domain conversion operation, and the like.
- a preprocessing process for obtaining input data for the artificial neural network for classification of a road will be described in detail with reference to FIGS. 6 to 8 .
- the input data acquired through the preprocessing process may be input to the artificial neural network for classification of the road surface.
- the road classification artificial neural network according to various embodiments of the present disclosure may be trained with a learning data set composed of a plurality of data obtained for various road surfaces in order to classify the road surface.
- the learned road classification artificial neural network may output a result based on input data.
- the output result according to an embodiment of the present disclosure may include information related to a probability value for each classification class of the road surface.
- a probability that the target road surface corresponds to each of the plurality of road surface types may be expressed as a numerical value and output.
- one or more classes of the output road surface may be output in order of high probability.
- An output result according to another embodiment of the present disclosure may be output by determining a specific class among a plurality of classes.
- the specific class may be a case where the probability value for the corresponding class is greater than or equal to the threshold value, or the probability difference with the second-ranked class is greater than or equal to the threshold value.
- the output result of the artificial neural network for classifying the road surface is information related to the material or condition of the road surface, and is not limited to the above example, and may be output in a form required by the user according to the design of the artificial neural network. .
- the road classification device may perform various operations according to the output result. By changing or adding a control operation based on the road classification result, the accuracy of the result or the efficiency of road management may be improved.
- the road classification device may change the transmission period or frequency of the sound wave signal according to the output result.
- a command or signal for controlling the road surface is generated and transmitted through the road surface management device.
- a specific class eg, snow, ice, or slush
- An embodiment of managing the road surface according to the output result will be described in detail with reference to FIG. 12 .
- FIG. 4 is a diagram illustrating a sound wave signal transmitted from a road classification device according to various embodiments of the present disclosure on a time axis.
- sound wave signals may be emitted multiple times within one transmission period.
- a set of sound wave signals transmitted within one transmission period in order to determine a road surface condition is referred to as a burst.
- the number of sound wave signals included in one burst may be changed according to a user setting or a predetermined rule. Also, intervals between sound wave signals included in one burst may be changed according to user settings or preset rules. Intervals between sound wave signals included in a burst may or may not be constant. Intensities of sound wave signals included in one burst may be the same or different from each other.
- the number, interval, intensity, and duration of a burst of sound wave signals included in one burst are referred to as a burst configuration.
- the different bursts may have the same or different burst configurations.
- the burst configuration for each burst can be changed according to user settings or predetermined rules.
- the number of sound wave signals included in a burst may be one.
- the number of sound wave signals included in a burst may be plural.
- the transmission period means a transmission interval of bursts for the road classification device to classify the state or material of the target road surface.
- the transmission period may mean a time interval between adjacent sound wave signals that are regularly transmitted. Referring to FIG. 4 , the transmission period may correspond to a time interval between an initial signal 1a included in one burst (burst 1) and an initial signal 2a included in the next burst (burst 2).
- the transmission period may be changed according to user settings or predetermined rules.
- the number and/or transmission period of sound wave signals included in a burst may be changed according to a result of road surface classification or weather conditions. For example, in a specific weather condition, such as when it snows or the temperature is below freezing, the number of sound wave signals transmitted may be increased or the transmission period may be shortened to improve the accuracy of road surface classification. A specific embodiment for this will be described in detail with reference to FIGS. 10 and 11 .
- a transmission period may vary according to a location or an object where a road classification device is installed. This is to distinguish the received signal reflected from the road surface and the crosstalk signal generated by the signal transmitted from the transmitter, and the transmission period of the road classification device installed in the road infrastructure is greater than that of the road classification device installed in the vehicle can be long Therefore, the judgment cycle of the road surface classification device installed in the road infrastructure may be longer than the judgment period of the road surface classification device installed in the vehicle.
- the road classification apparatus may measure or determine ToF of a target road surface or object.
- the road classification apparatus may transmit one or a plurality of sound wave signals and determine the ToF for the target road surface or object based on the received signal for the sound wave signals.
- ToF may be determined based on a distance between the road classification device and the target road surface.
- the road classification apparatus may determine an appropriate transmission period and burst configuration based on the determined ToF, and may transmit with the determined transmission period and burst configuration.
- the transmission period according to an embodiment of the present disclosure may be set longer than the ToF for the road surface.
- a duration of a burst according to an embodiment of the present disclosure may be set shorter than a transmission period.
- One result corresponding to one burst may be output as a road surface classification result for the target road surface by the road surface classification apparatus according to various embodiments of the present disclosure.
- the road classification device may display classification results for all sound wave signals included in one burst.
- the corresponding result may be output based on a plurality of classification results for each of a plurality of sound wave signals included in the burst.
- a first result is a road surface classification result obtained based on a signal in which a first burst (burst 1) is reflected on the road surface.
- the first result may be a result obtained based on a result of the road surface classification of each of the signals 1a, 1b, 1c, and 1d included in the first burst.
- the most frequent values of the results of 1a, 1b, 1c, and 1d can be output as the result.
- the road surface classification result for the first burst may be output based on an average value obtained by summing the results of steps 1a, 1b, 1c, and 1d.
- a time interval between road classification results of adjacent bursts that is, a time interval between a first result and a second result may be referred to as a determination period for road classification.
- the determination period may coincide with the transmission period.
- the determination period since the output timing may be irregular according to the signal processing operation, the determination period may not be constant and may not coincide with the transmission period.
- the road classification apparatus may change the transmission period to change the determination period.
- the determination period may be changed according to a user setting or a predetermined rule. A specific embodiment of changing the determination period will be described in detail with reference to FIGS. 10 and 11 .
- FIG. 5 is a diagram illustrating a transmission period of a sound wave signal and a reception period of a reflected signal according to an embodiment of the present disclosure.
- the road classification device may transmit a burst or sound wave signal in a transmission period.
- a case in which one signal is transmitted is illustrated for convenience of description, but the present disclosure is not limited thereto. That is, in the present disclosure, it may be understood that transmission of a sound wave signal by a road surface classification device includes not only single-shot transmission of one signal, but also transmission of a burst composed of a plurality of signals with a period.
- the road classification apparatus may determine the ToF of the transmitted sound wave signal for the road, and thus may predetermine a corresponding reception interval for one transmission interval.
- the road classification device when a signal is detected by the receiver before the reception period, the road classification device may regard it as a noise signal or a crosstalk signal, and may control a transmitter of the road classification device to reduce it. there is.
- the strength of the first signal received before the reception period is greater than the first threshold, or the strength of the second signal received during the reception period and the first signal received before the reception period
- the difference in intensity is smaller than the second threshold
- power supplied to the transmitter may be changed to control the difference.
- the first threshold value and/or the second threshold value may be predetermined or may be set by a user input or an external device.
- vibration of the transmitter may be controlled by adjusting the amount of power supplied to the transmitter.
- FIG. 6 is a diagram illustrating a target on which a road classification device according to various embodiments of the present disclosure is installed.
- the road classification device 100 may be installed on a moving object 610 or a road infrastructure 620.
- the road classification device 100a installed in the moving object 610 such as a vehicle
- the road classification device 100b installed in the road infrastructure 620 have different heights from the road surface, the ToF of the transmitted sound waves is also different from each other.
- the road classification apparatus of the present disclosure uses an artificial neural network to classify a road surface based on a reflected signal of the road surface, many data sets are required to train the artificial neural network.
- FIG. 7 is a diagram illustrating a method of obtaining a data set for learning a road classification artificial neural network according to various embodiments of the present disclosure.
- a learning data set for learning a road classification artificial neural network is obtained for various road surfaces by road classification (class) using a transceiver included in a mobile measurement device 700 It can be.
- road classification class
- the mobile measuring device 700 of the present disclosure refers to a sensor device mounted on equipment that moves on a road such as a bicycle, a car, or a scooter, and may include equipment that can be moved by humans or mechanical devices.
- the ToF of the learning data collected by the mobile measurement device 700 may be similar to the ToF of the road classification device 100a installed in the moving object 610 such as a vehicle of FIG. 6 .
- the position of the mobile measuring device on the ground may be set in consideration of the position of the road classification device installed on the mobile body on the ground.
- the road classification artificial neural network learned with the learning data set acquired by the mobile measurement equipment according to various embodiments of the present disclosure can be used directly without any correction for the reflected signal in the road classification device 100a installed in the moving object. there is.
- the road classification device when the road classification device is installed at a different height from a moving object such as a road infrastructure (100b), if the reflected signal obtained by the road classification device is input as it is to the road classification artificial neural network, the classification accuracy for the target road surface is increased. may fall
- FIG. 8 is a flowchart illustrating a process of pre-processing a received reflected signal by a road classification apparatus according to various embodiments of the present disclosure.
- the pre-processing process of FIG. 8 is an example for expressing the technical idea of the present disclosure, and according to various embodiments, more operations than the operations shown in FIG. 8 or at least one less operation may be performed. there is.
- the road classification apparatus may obtain first data based on the received reflection signal.
- the road classification device of the present disclosure may convert the reflected signal into a digital signal through the ADC circuit included in the controller 130.
- the transmitter/receiver included in the road classification device may obtain first data by processing a reflected signal reflected through the road in the form of a digital signal.
- the road classification apparatus may acquire second data by applying atmospheric correction to data converted into digital signals.
- the road classification apparatus may generate second data obtained by correcting an attenuation amount of a reflected signal received based on atmospheric information such as temperature, humidity, and atmospheric pressure acquired through an atmospheric sensor.
- the propagation distance of sound waves required for atmospheric correction may be previously input by a user or may be obtained based on ToF. That is, depending on the location where the road classification device is installed, distance information on the road surface is input in advance, or distance information on the road surface is obtained based on ToF information and waiting information obtained by the road classification device as described above. can
- the road classification apparatus may obtain third data by applying distance correction to the second data for which the atmospheric attenuation is corrected.
- the sound wave signal which is the basis of the learning data of the artificial neural network for classification of the road according to various embodiments of the present disclosure, may be a signal obtained by being reflected at a distance of d1 from the road surface. . Therefore, in order to improve the classification performance of the road classification device 100b installed at a height d2 different from d1, the sound wave signal obtained at d2 may be corrected as if it were the sound wave signal obtained at d1.
- steps 802 and 803 may be performed as one procedure. That is, according to various embodiments of the present disclosure, sound wave data obtained by correcting the atmospheric attenuation and the distance to the road surface may be obtained based on the atmospheric information and the distance information for the digital signal obtained in step 801 .
- steps 802 and/or 803 may be omitted according to the installation location of the road classification device according to various embodiments of the present disclosure.
- the road classification apparatus may obtain frequency domain data by performing transformation to analyze the corrected sound wave data in a frequency domain.
- the frequency domain conversion method according to various embodiments of the present disclosure is as described above.
- the obtained frequency domain data is input data to the artificial neural network for classification of roads according to various embodiments of the present disclosure.
- the neural network for classification of roads outputs a result of classification of the road surface for the target road surface. can do.
- the road classification apparatus may output a result based on additional information other than the sound wave signal.
- Other information that can be acquired in addition to the sound wave signal may include image information acquired through a vision sensor (camera), road surface temperature information obtained through an IR sensor, environment information obtained through a communication unit, and the like.
- the road classification device may combine two or more different criteria.
- the road classification apparatus may further include a separate image-based road classification artificial neural network for obtaining a road classification result for image information.
- the road surface classifying apparatus may verify a result value for a specific road surface condition by adding a specific temperature condition. For example, if the road surface temperature is higher than 0 degrees Celsius, ice cannot be physically formed under atmospheric pressure conditions, so if the road surface classification result is classified as ice under the corresponding temperature condition, it may be determined that it corresponds to an error. Therefore, if the road surface or air temperature acquired through the IR sensor or atmospheric sensor of the sensing unit is confirmed to be above a certain temperature, if the road surface condition indicated by the road surface classification result is ice-related, an additional action may be performed instead of outputting the corresponding result. can Alternatively, when the road surface temperature is higher than or lower than a specific temperature, it may be set to output the result by further utilizing the result of the image information.
- the road surface classification apparatus may output a road surface classification result by further considering weather environment information. For example, when meteorological environment information related to weather, such as when it snows or rains, is received, the ranking of the road surface classification result for a class with a high possibility of being classified in the corresponding weather may be adjusted.
- the road classification artificial neural network can enhance learning performance and classification performance by receiving additional related data instead of learning only data based on sound wave signals.
- FIG. 9 is a diagram illustrating a multi-modal artificial neural network according to an embodiment of the present disclosure.
- a road classification artificial neural network may include a multi-modal artificial neural network.
- the multi-modal artificial neural network can function as one classifier through classifiers based on different information by inputting at least one of image information, air information, or road temperature information in addition to input data related to sound waves.
- a more accurate road surface classification result may be obtained by inputting a plurality of pieces of information related to one road surface condition together. That is, the road classification apparatus according to various embodiments of the present disclosure may output a road surface result by combining a plurality of pieces of information.
- the input data shown in FIG. 9 is exemplary, and only a part of image information, atmospheric information, and/or road surface temperature information or additional information may be further utilized.
- FIG. 10 is a flowchart illustrating an operation of changing a control operation based on a predetermined control change trigger by a road surface classification apparatus according to an embodiment of the present disclosure.
- a control change trigger refers to a situation or condition for changing an operation of a road classification device according to various embodiments of the present disclosure, and may be set in advance by a user or by a command from an external device. there is.
- control change trigger means that the method set before the occurrence of the control change trigger in the road classification device, such as burst configuration, transmission period, judgment period, and road classification result output method, is changed. do.
- the control change trigger may include a change in a road surface classification result (class), an output of a specific class, weather conditions, time conditions, or geographic conditions, but is not limited to the above examples.
- a control change trigger when a road classification result is changed, an operation of the road classification device may be changed.
- FIG. 11 is a diagram illustrating a scenario in which a road surface classification result is changed according to an embodiment of the present disclosure.
- the road surface classification result of the road surface classification device is a first class R1 at a first time point t1 and a second class R2 at a second time point t2.
- the second class may be a different class from the first class.
- the second class may indicate a road surface condition related to ice
- the first class may be a classification result related to other road surface conditions.
- the road classification apparatus may need to change a control operation.
- the road classification apparatus may change a transmission period or a burst configuration in order to determine whether an error has occurred in the road classification result. That is, the number of determinations may be increased by shortening the transmission period, or the number of determinations may be increased by increasing the number of sound wave signals included in the burst. Alternatively, instead of immediately changing the transmission period or burst configuration, whether to change the transmission period or burst configuration may be determined based on a later decision.
- the road classification device since the result of the second time point is different from the result of the first time point (R1 ⁇ R2), the road classification device according to an embodiment of the present disclosure controls the transmission period to be shortened. and more results can be obtained during a short time interval (t3 to t6). Meanwhile, since the number of determinations to the second class is greater than the number of determinations to the first class during the corresponding time interval (t3 to t6), the road classification device determines that the determination to the second class is accurate and sets the transmission period back to the original one. state, and the result can be output at the seventh time point t7, which is the time point according to the changed transmission period.
- the first class R1 is determined at the first time point t1, and the second time point t2
- the accuracy of the determination of the second class based on the result of the third class at the third time point which is the next judgment time point, It is also possible to determine whether to change the transmission period or the like.
- the transmission period may not be changed, and when the result of the third class is not determined to be R2, the determination of R2 is determined as an error, and the transmission period can be changed.
- the determination result at each time point may be a determination result corresponding to each burst according to various embodiments of the present disclosure.
- the road classification apparatus may further perform an operation related to road management based on a plurality of determination results in the changed control operation. For example, after determining the accuracy of a specific class that has been changed, the determination of the corresponding class may be considered correct, and a road surface management operation related to the changed class may be performed. Details related to the road surface management operation will be described with reference to FIG. 12 .
- control change trigger when a weather condition or a time condition is changed, the operation of the road classification device may be changed.
- the road classification apparatus may shorten a transmission period or reduce the number of transmissions within a burst in order to quickly determine whether or not black ice has occurred.
- the control operation can be changed by stretching, etc.
- a weather environment such as strong wind, rain, or heavy snow. may be
- a transmission period or burst configuration may be changed at a specific time in consideration of this point.
- the control operation may be changed by lengthening the transmission period or reducing the number of transmissions within a burst to reduce power consumption.
- a control change trigger when a geographical condition is changed, the operation of the road classification device may be changed.
- the road classification device When the road classification device is installed in the road infrastructure, the geographical conditions cannot be changed, but the transmission period or burst configuration may be different for each regional condition.
- a transmission period or burst configuration When the road classification device is installed in a moving object such as a vehicle, a transmission period or burst configuration may be different when entering a specific area. For example, when black ice enters a vulnerable section and the road classification device receives corresponding information, the control operation may be changed as described above.
- control change trigger related to weather conditions, time conditions, or geographic conditions is illustrative and not limited thereto, and may be set by a user input or a signal received from an external electronic device such as a server device.
- FIG. 12 is a diagram illustrating a road surface management method by a road classification device according to various embodiments of the present disclosure.
- the road classification device may obtain information related to road surface control.
- the information related to the control of the road surface may include a result obtained in step 304 of FIG. 3 or a final result obtained through changing the control operation of FIG. 10 .
- the information related to the control of the road surface may include weather information and/or road surface temperature information acquired by the road classification device.
- the road classification apparatus may determine whether an operating condition for road surface control is satisfied based on the acquired information.
- the road surface classification device sets a road surface management device installed on the road surface to solve or prevent the icy state of the road surface. It can be determined that the conditions for operation are satisfied.
- operating conditions of the road surface control may be determined by combining the obtained road surface classification result and weather information. For example, if the weather information satisfies a specific condition, it is determined that the risk of ice formation is high, and it is determined that the condition for operating a road management device installed on the road surface to relieve or prevent the icy state of the road surface is satisfied.
- Examples of weather information for operating the road surface management device may include the following conditions.
- the road surface classification result is obtained as a specific class (eg, water, slush, ice). It may be determined that the road surface control is necessary.
- a specific class eg, water, slush, ice
- a road surface management device may include a salt spray device or a hot wire, but is not limited thereto.
- the road classification apparatus may generate a road surface control signal based on the obtained information and determination.
- the road surface control signal may include a signal or command required to control the road surface management device installed on the road surface.
- a road surface classification device may be interlocked with a road surface management device installed on a road.
- the road classification device may generate a command signal for controlling the road management device and transmit it to the road management device.
- the road classification device may generate a signal instructing control of the road management device and transmit the signal to the external server.
- the road surface management device when the road surface management device receives the road surface control signal, it may perform an operation of controlling the road surface based on the road surface control signal. For example, the road surface management device may spray salt water or operate a heating wire based on the road surface control signal.
- the road surface classification device may determine the risk of damage to the road surface.
- Asphalt can be damaged by repeated passage of vehicles exceeding a certain weight.
- the volume expands, and at this time, when a large vehicle such as a truck passes through, the road surface may be damaged.
- a road classification device installed in a road infrastructure may periodically detect ToF of a road surface, and thus may measure traffic information such as passing vehicle information and traffic volume based on this.
- FIG. 13 is a diagram illustrating that a road classification apparatus according to an embodiment of the present disclosure collects traffic information.
- the road classification device may collect road traffic information based on ToF measurement.
- the traffic information collected by the road classification apparatus may include information related to a degree of road surface damage or traffic volume.
- ToF corresponding to the installation height of the road classification apparatus may be determined as the reference ToF. That is, the ToF of the reflected signal reflected from the road surface may be referred to as the reference ToF.
- the road classification apparatus may determine that there is no vehicle on the road when it is identified that the ToF obtained by the road classification apparatus corresponds to the reference ToF. In addition, when it is identified that the obtained ToF is shorter than the reference ToF, it may be determined that there is a vehicle on the road. In addition, information on the size (height) of an object on the road surface estimated based on the obtained ToF may be obtained.
- the road classification device may determine that a large vehicle has passed in response to a signal having a shorter ToF value.
- a criterion for determining a large vehicle may be set in advance by a user input or a signal from an external device.
- the road classification apparatus may estimate the amount of traffic passing on the road surface during a predetermined time interval based on the ToF value obtained during the predetermined time interval.
- the traffic volume information acquired by the road classification apparatus of the present disclosure may further include information related to the size of vehicles passing through.
- ToF 1 in (a) where a large vehicle is passing is smaller than ToF 2 in (b) where a small vehicle is passing.
- the road classification apparatus may obtain road surface condition information and/or weather information, it may determine the risk of damage to the road surface by combining the obtained information and traffic information, and may inform the outside of the road surface condition information.
- the road surface condition information may include a road surface classification result and/or road surface temperature information.
- information on the number of passages of large vehicles during a period in which the road surface classification result is determined to be an ice-related class may be measured, and related information may be provided to a user or an external device.
- the external device may include a server device of an organization that manages roads.
- information on vehicle traffic during a period in which the road surface temperature is measured to be less than or equal to a specific temperature may be acquired and transmitted to an external device.
- the degree of damage to the road surface may be estimated based on a result of a specific road surface classification or a traffic volume of large vehicles under a specific weather condition.
- the risk of damage to the road surface may be managed by providing the acquired traffic volume information of large vehicles to an external device.
- the road classification apparatus may determine whether to use the received signal for road classification or to collect traffic information based on the ToF of the received signal. That is, if the ToF of the obtained received signal is within the error range of the reference ToF, it can be determined as a reflection signal from the road surface and used for classification of the road surface. Based on the determination, traffic information may be obtained.
- the road classification device may shorten the transmission period of the sound wave signal than the transmission period for road classification. That is, the transmission period of the sound wave signal may be set in various ways according to the needs of the user, and the acquired signal may be variously processed according to the purpose.
- the road surface classifying device of the present disclosure may include a road surface type estimating device.
- the following road surface type estimating device is various embodiments of the road surface classification device of the present disclosure. It is self-evident that this can be done.
- FIG. 14 is a configuration diagram of a road surface type estimation device according to an embodiment of the present disclosure.
- the apparatus for estimating the type of road surface using sound waves includes a sound wave transceiver 1410, a signal converter 1420, an artificial neural network 1430, and a controller (MCU) ( 1440) may be included.
- the road surface type estimating device may further include an atmospheric attenuation correction unit (not shown) and an atmospheric information measuring unit (not shown).
- the sound wave transmission/reception unit 1410 may transmit a sound wave signal to a corresponding road surface for which the type is to be determined, and then receive the reflected signal.
- the sound wave transmitting/receiving unit 1410 includes a sound wave transmitter 1411 outputting a transmission signal under the control of the control unit 1440, and a sound wave receiver 1412 receiving a reflected signal after the transmission signal is reflected on an arbitrary surface. ) may be included.
- the signal converter 1420 may obtain a frequency domain signal (eg, a spectrogram) by performing frequency conversion on a predetermined region in the time domain of the received signal.
- a frequency domain signal eg, a spectrogram
- the signal converter 1420 may include a short-time Fourier transform (STFT) converter, a fast Fourier transform (FFT), a cepstrum, or a wavelet transform.
- STFT short-time Fourier transform
- FFT fast Fourier transform
- cepstrum cepstrum
- wavelet transform a wavelet transform
- the frequency domain signal (spectrogram) may be 2D or 3D.
- the artificial neural network 1430 may use the frequency domain signal (spectrogram) as an input signal, extract and classify characteristics of the input signal based on the learned road surface classification model, and estimate the type of the road surface.
- spectrogram frequency domain signal
- the signal converter 1420 may include an analog-to-digital converter (ADC).
- ADC analog-to-digital converter
- the ADC may convert an analog signal of the received signal into a digital signal.
- An atmospheric attenuation correction unit (not shown) may calculate and correct the atmospheric attenuation of the digital signal.
- the artificial neural network 1430 takes the converted signal or the corrected digital signal as an input signal, performs convolution on the input signal based on the learned road surface classification model, classifies it, and estimates the type of the road surface.
- decision trees linear discriminant analysis
- logistic regression classifiers logistic regression classifiers
- naive Bayes classifiers support vector machines machine
- nearest neighbor classifiers and ensemble classifiers
- Decision trees include Fine tree, Medium tree, Coarse tree, All tree, and Optimizable tree
- linear discriminant analysis includes Linear discriminant, Quadratic discriminant, All discriminants, and Optimizable discriminant.
- the Naive Bayes classifier includes Gaussian Naive Bayes, Kernel Naive Bayes, All Naive Bayes, and Optimizable Naive Bayes
- the support vector machine (SVM) includes Linear SVM, Quadratic SVM, Cubic SVM, and Fine Gaussian.
- SVM SVM
- Medium Gaussian SVM Coarse Gaussian SVM, All SVM
- Optimizable SVM and nearest neighbor classifiers include Fine KNN, Medium KNN, Coarse KNN, Cosine KNN, Cubic KNN, Weighted KNN, All KNN, It includes Optimizable KNN, and ensemble classifiers may include Boosted trees, Bagged trees, Subspace Discriminant, Subspace KNN, RUSBoosted trees, All Ensembles, and Optimizable Ensembles.
- the controller (MCU) 1440 may control operations of the sound wave transceiver 1410 , the signal converter 1420 , and the artificial neural network 1430 .
- the signal converter 1420 and the artificial neural network 1430 express software implemented as a program as a component.
- the apparatus for estimating the type of road using sound waves includes a storage (memory) in which the learned road classification model and software implemented as the program are stored.
- the storage (memory) may be included in the controller (MCU).
- the road surface type estimation device using sound waves may further include an atmospheric sensor (not shown) capable of measuring temperature, humidity, and air pressure in the air.
- the atmospheric information including the temperature, humidity, and air pressure may be used in the atmospheric attenuation correction unit or transmitted as an input to the artificial neural network 1430 .
- 15 is a diagram for explaining a transmission signal and a reception signal in an apparatus for estimating a type of road surface using sound waves according to an embodiment of the present disclosure.
- the controller (MCU) 1440 transmits a trigger signal having a preset magnitude (v: trigger voltage) and a preset transmission period (p: transmission period) to the sound wave transceiver 1410.
- v trigger voltage
- p transmission period
- the sound wave transmitter 1411 of the sound wave transceiver 1410 may output a sound wave signal 1501 having a specific frequency, for example, 40 kHz, to a corresponding road surface for which the type is to be known.
- the sound wave receiver 1412 of the sound wave transceiver 1410 may receive a reflected signal reflected from the road surface and returned.
- the signal 1502 received on the same timeline as the sound wave signal 1501 may be a crosstalk signal of the sound wave signal transmitted by the sound wave transceiver 1410 .
- the control unit 1440 may determine, as the received signal, the signal 1503 for a preset time from the point where the amplitude received after the transmission delay is the largest.
- t_0 is the point at which the amplitude of the signal received after the crosstalk signal is the largest
- a total of (a+b) ms can be observed from t_0 - a [ms] to t_0 + b [ms]
- a is 0.2 and b is 5.
- a and b are variable values that can be adjusted.
- 10 ms which is the time until the transmitted sound wave signal sufficiently disappears, is set as one transmission period, and the sampling frequency of the sound wave transceiver 1410 is set to 1 MHz, sampling at 25 times the 40 kHz sound wave frequency.
- the state of the road surface may be detected by detecting a plurality of received signals according to the transmission period, or the state of the road surface may be detected by processing a reflected signal received after transmitting a sound wave once. there is.
- 16 is a diagram for exemplarily explaining a signal converter in an apparatus for estimating a type of road surface using sound waves according to an embodiment of the present disclosure.
- the STFT converter excludes the crosstalk signal 1502 of the sound wave signal transmitted by the sound wave transceiver 1410 among the reflected signals received in FIG.
- a 2D spectrogram 1602 may be obtained by performing a short-time Fourier transform on the signals 1503 and 1601 during time.
- the signal 1503 for one period may be Fourier-transformed, or the received signal for multiple periods may be Fourier-transformed.
- materials may be classified using acoustic impedance and surface roughness information.
- Acoustic impedance is not a constant, and its value may vary for each frequency at which sound waves vibrate. Therefore, analysis in the frequency domain may be useful.
- a Time Fourier Transform which is one of several methods for transforming a received signal in the time domain into a frequency domain signal, may be used.
- a Short-Time Fourier Transform may be used to check the FFT at every hour (sampling time).
- frequency analysis can be performed using not only Short-Time Fourier Transform but also wavelet, etc.
- the STFT was used for this purpose.
- STFT Short-Time Fourier Transform
- Wavelet Transform may be used to overcome the limitation of resolution due to the trade-off relationship between frequency and time.
- STFT is performed several times while changing the window length.
- wavelet functions include Morlet, Daubechies, Coiflets, Biorthogonal, Mexican Hat, and Symlets.
- 17 is a diagram for explaining an artificial neural network in an apparatus for estimating a road surface type using sound waves according to an embodiment of the present disclosure.
- the artificial neural network is a deep neural network (DNN) of a multi-layer perceptron algorithm including an input layer 1701, a plurality of hidden layers 1702, and an output layer 1703. neural networks).
- the artificial neural network may include a deep convolution neural network (DCNN) of a multi-layer perceptron algorithm further including a convolution performer (not shown). there is.
- DCNN deep convolution neural network
- the input layer 1701 can flatten the data of the spectrogram 1702 and receive input in 1D.
- Data input to the input layer 1701 may be extracted and classified through a plurality of hidden layers 1702 .
- the output layer 1703 may output a probability value for each type of the learned road surface.
- the artificial neural network may determine and output the type of road surface having the highest probability among probability values output from the output layer 1703 using softmax 1704 .
- the artificial neural network may receive atmospheric information (temperature, humidity, atmospheric pressure information) and use it as an input of the input layer 1701 .
- the artificial neural network can also be used as an input of the input layer 1701 by Fourier transforming the sound wave signal 1501 transmitted to the road surface.
- the convolution performer performs a convolution operation multiple times on the received digital input signal, and for each convolution operation, batch normalization, ReLU function, and MaxpPooling ) function, and the data flattened by the last convolution operation can be output to the transfer layer.
- the transfer layer is the input layer 1701 of the CNN, and can receive the flattened output data of the convolution performer in one dimension (1D), and subsequent operations are the same as above.
- 18 is a diagram for explaining the operation of a convolution performer.
- the convolution performer performs a 1D convolution operation multiple times (eg, 5 times) on the input signal, and performs batch normalization, a ReLU function, and a MaxpPooling function for each convolution operation. and the output of the last convolution operation may be flattened data.
- an input signal 1801 becomes about 7000 received signals for 7 ms
- the result of performing the first convolution 1802 is 1D conv (64,16), BN , ReLU, and MP(8)
- the second convolution result 1803 is 1D conv (32,32), BN, ReLU, and MP(8)
- the third convolution result 1804 is the result of performing 1D conv (16,64), BN, ReLU, and MP(8) on the second convolution result 403
- the fourth The convolution result 1805 is the result of performing 1D conv (8,128), BN, and ReLU on the third convolution result 1804, and the fifth convolution result 1806 is the fourth convolution result 1805 ) is the result of performing 1D conv (4,2568), BN, and ReLU.
- 19 is a diagram for explaining a code of a convolution performer of an apparatus for estimating a road surface type using sound waves according to an exemplary embodiment of the present disclosure.
- FIG. 19 is a code implemented by software in part of the convolution performer shown in FIG. 18 .
- the code may include a plurality of batch normalization (BatchNorm) functions and a max pooling function (MaxPool).
- BatchNorm batch normalization
- MaxPool max pooling function
- a method of performing a one-dimensional (1D) convolution operation has been described as an example, but not only 1D, but also 2D and 3D convolution operations are possible.
- 20 is a flowchart of a method for estimating a type of road surface using domain conversion of sound waves according to an embodiment of the present disclosure.
- a learning step (2001) may be preceded to generate a road surface classification model.
- the learning step 2001 after transmitting a sound wave signal for multiple types of road surfaces, the reflected signal is received and the signal is converted into a frequency domain signal (eg, a spectrogram), and the frequency domain signal (spectrogram) is received. ) may be input to the artificial neural network to learn the road classification model.
- a frequency domain signal eg, a spectrogram
- a Short-Time Fourier Transform (STFT) converter may be used to convert the frequency domain into a frequency domain signal.
- the frequency domain signal may be 2D or 3D.
- a sound wave signal may be transmitted to a corresponding road surface for which the type is to be determined, and then the reflected signal may be received (2002).
- a frequency domain signal may be obtained by performing signal conversion on a preset region of the received signal (2003).
- the frequency domain signal acquisition step (2003) in the received signal, except for the crosstalk signal of the transmitted sound wave signal, for each period of the sound wave signal, the signal for a preset time received after the transmission delay
- the frequency domain signal may be obtained by performing domain conversion on the frequency domain.
- the frequency domain signal may be used as an input signal of the artificial neural network, and characteristics of the input signal may be extracted and classified based on the learned road surface classification model to determine the type of the road surface ( 2004).
- the artificial neural network may include a deep neural network (DNN) of a multi-layer perceptron algorithm including an input layer 1701, a plurality of hidden layers 1702, and an output layer 1703. there is.
- the output layer 1703 can output a probability value for each type of the learned road surface, and the artificial neural network uses softmax 1704 to determine the type of road surface with the highest probability. can be determined and published.
- the artificial neural network may receive atmospheric information (temperature, humidity, air pressure information) and use it as an input of the input layer.
- the artificial neural network may also be used as an input of the input layer by performing Fourier transform on the sound wave signal transmitted to the road surface.
- 21 is a flowchart illustrating an embodiment of a method for estimating a type of road surface using sound waves according to the present disclosure.
- a learning step 2101 may be preceded to generate a road surface classification model.
- the road surface classification model may be learned by performing an operation.
- a sound wave signal may be transmitted to a corresponding road surface for which the type is to be determined, and then the reflected signal may be received (2102).
- the analog signal may be converted into a digital signal for a predetermined area of the received signal (2103).
- the point where the amplitude of the signal received after the transmission delay is the largest is referenced for each period of the sound wave signal, excluding the crosstalk signal of the transmitted sound wave signal, in the received signal.
- the signal for a predetermined time can be converted into a digital signal.
- t_0 is the point at which the amplitude of the signal received after the crosstalk signal is the largest
- a total of (a+b) ms can be observed from t_0 - a [ms] to t_0 + b [ms]
- a and b can be variably adjusted according to the environment or conditions.
- multiple convolution operations may be performed in the artificial neural network by receiving the digital signal (2104).
- a convolution operation is performed on the digital signal multiple times, and batch normalization, a ReLU function, and a MaxpPooling function may be performed for each convolution operation, , the output of the last convolution operation is the flattened data.
- a method of performing a one-dimensional (1D) convolution operation has been described as an example, but not only 1D, but also 2D and 3D convolution operations are possible.
- the type of the road surface may be determined by extracting and classifying the characteristics of the convolutional signal (flattened data) based on the road surface classification model learned in the artificial neural network ( 2105).
- the artificial neural network includes a convolution performer for receiving the digital signal and performing multiple convolution operations, a transfer layer, a multi-layer perceptron algorithm including a plurality of hidden layers and an output layer DCNN : Deep Convolution Neural Network).
- the output layer may output a probability value for each type of the learned road surface, and the artificial neural network may determine and output the type of road surface having the highest probability using softmax. .
- the artificial neural network may receive atmospheric information (temperature, humidity, air pressure information) and use it as an input to the convolution unit.
- the artificial neural network may also use the sound wave signal transmitted to the road surface as an input to the convolution performer.
- FIG. 22 is a flowchart illustrating a method for estimating a road surface type using sound waves in which atmospheric attenuation is corrected according to an embodiment of the present disclosure.
- a learning step 2201 may be preceded to generate a road surface classification model.
- sound wave signals are transmitted for multiple types of road surfaces, reflected signals are received, the signals are converted into digital signals, and attenuation in air is corrected for the converted digital signals.
- the frequency domain signal is converted into a frequency domain signal, and the frequency domain signal is input to a neural network to learn a road surface classification model.
- a Short-Time Fourier Transform (STFT) converter a Fast Fourier Transform (FFT), a cepstrum, or a wavelet transform is used to transform the signal into the frequency domain signal.
- STFT Short-Time Fourier Transform
- FFT Fast Fourier Transform
- cepstrum a cepstrum
- wavelet transform a wavelet transform
- a sound wave signal may be transmitted to a corresponding road surface for which the type is to be determined, and then the reflected signal may be received (2202).
- an analog signal may be converted into a digital signal for a predetermined area of the received signal (2203).
- the point where the amplitude of the signal received after the transmission delay is the largest is referenced for each period of the sound wave signal, excluding the crosstalk signal of the transmitted sound wave signal, in the received signal.
- the signal for a predetermined time is converted into a digital signal.
- t_0 is the point at which the amplitude of the signal received after the crosstalk signal is the largest
- a total of (a+b) ms can be observed from t_0 - a [ms] to t_0 + b [ms]
- a and b can be adjusted according to the environment or conditions.
- the amount of attenuation in air of the digital signal may be calculated and corrected (2204).
- the atmospheric attenuation may be calculated and corrected using the following ⁇ Equation 1> to ⁇ Equation 8>.
- the atmospheric attenuation correction step may be performed by a control unit or an atmospheric attenuation correction unit that is software implemented as a program.
- the saturation pressure (Psat) may be calculated using Equation 1 below.
- To1 is the triple point of the atmosphere [K]
- T is the current temperature [K].
- the absolute humidity (h) can be calculated using Equation 2 below.
- hrin is the relative humidity [%]
- Psat is the saturation pressure [unit]
- Ps is the static pressure [atm].
- T is the current temperature [K].
- Equation 4 the scaled relaxation frequency for oxygen (FrO), which accounts for 21% of the atmosphere, can be calculated using Equation 4 below.
- the attenuation coefficient ( ⁇ : attenuation coefficient [nepers/m]]) may be calculated using Equation 5 below.
- Ps is the static pressure
- F is the frequency of the sound wave signal (transmission sound wave signal)
- T is the current temperature [K]
- To is the reference temperature [K]
- FrO is the extended relaxation frequency of oxygen
- FrN is the extended relaxation frequency of nitrogen.
- the attenuation ratio (A, unit: dB) of the sound wave signal may be calculated using Equation 6 below.
- ⁇ is an attenuation coefficient
- d is the distance between the sound wave transceiver 100 and the road surface to be determined.
- the d may be calculated using the following ⁇ Equation 7> using the time of flight t (time of flight) and the speed of sound in the air (Vair) from being transmitted by the transmitter to being reflected on the road surface and being detected by the receiver. there is.
- t is the required time
- Vair is the speed of sound in air [m/s].
- Equation 8 the speed of sound in air
- Ks is the isentropic volumetric expansion coefficient of the object (coefficient of stiffness)
- ⁇ is the density of the object (atmosphere).
- the speed of sound in the air may be corrected according to the temperature, air pressure and humidity of the air and used for attenuation compensation.
- a frequency domain signal may be obtained by performing signal conversion on a preset region of the corrected digital signal (2205).
- the frequency domain signal acquisition step 2205 except for the crosstalk signal of the transmitted sound wave signal in the corrected digital signal, for each period of the sound wave signal, the signal for a predetermined time received after the transmission delay
- the frequency domain signal may be obtained by performing frequency conversion in a signal converter.
- the frequency domain signal may be used as an input signal of the neural network, and characteristics of the input signal may be extracted and classified based on the learned road surface classification model to determine the type of the road surface (2206). ).
- the neural network may include a deep neural network (DNN) of a multi-layer perceptron algorithm including an input layer, a plurality of hidden layers, and an output layer.
- DNN deep neural network
- the output layer may output a probability value for each type of the learned road surface, and the neural network may determine and output the type of road surface having the highest probability using softmax.
- the structure of the neural network is not limited to the aforementioned DNN.
- the neural network may receive atmospheric information (temperature, humidity, air pressure information) and use it as an input of the input layer.
- the neural network may frequency-convert the sound wave signal transmitted to the road surface and use it as an input of the input layer.
- a digital signal with a corrected amount of attenuation in air is received under the control of a controller and multiple convolution operations are performed in the artificial neural network.
- a 1D convolution operation is performed multiple times on the digital signal for which the attenuation in air is corrected, and a batch normalization, a ReLU function, and a MaxpPooling function are performed for each convolution operation. , and the output of the last convolution operation is the flattened data.
- characteristics of the convolutional signal may be extracted and classified to determine the type of the road surface.
- the artificial neural network When performing convolution, the artificial neural network further includes a convolution performer for receiving the digital signal and performing multiple convolution operations: Deep Convolution Neural Network (DCNN) of a multi-layer perceptron algorithm. ) may be included.
- the output layer may output a probability value for each type of the learned road surface, and the artificial neural network may determine and output the type of road surface having the highest probability using softmax.
- DCNN Deep Convolution Neural Network
- the structure of the artificial neural network is not limited to the aforementioned DCNN.
- the artificial neural network may receive atmospheric information (temperature, humidity, air pressure information) and use it as an input to the convolution unit.
- the artificial neural network may also use the sound wave signal transmitted to the road surface as an input to the convolution performer.
- 23 is a diagram for explaining a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure. 23 is a specific embodiment of the road infrastructure shown in FIG. 2 .
- a structure 2301 is located on or near a road 2300, and an acoustic sensor 2310 and a vision sensor 2320 are provided in the structure 2301.
- the sound wave sensor 2310 is provided on the structure 2301 so as to be located on the driving path of the vehicle on the road 2300 and perpendicular to the road surface, and the vision sensor 2320 captures the entire area of the road. It can be installed on the structure 2301.
- FIG. 23 illustrates a communication unit 2350 for transmitting data acquired from the sonic sensor 2310 and the vision sensor 2320 to a controller (not shown).
- the vision sensor 2320 is one of the mainstream technologies in the field of object recognition, detection, and segmentation, as solutions combined with artificial intelligence models are spreading in all fields of industry with the development of artificial neural networks. Due to the development of artificial intelligence technology, an algorithm that enables the vision sensor 2320 to operate similarly to a method in which a person intuitively recognizes an object from a photograph (image) and divides an area is being realized.
- recognizing an object using the acoustic wave sensor 2310 is possible through wave analysis of a signal reflected after hitting a surface to be recognized using a sound wave, and the reflected wave is generated according to the acoustic impedance or surface roughness of the target surface where the reflection occurs. use the determined principle. That is, the sound wave sensor 2310 can recognize black ice on the road because it is robust against external noise when a wide range of sound wave spectrum is used.
- One embodiment combines the advantages of a vision sensor capable of intuitively recognizing and distinguishing a wide area and a sound wave sensor technology that can accurately recognize a target without being affected by light sources using the physical properties of the target object to provide a wide range of road surfaces. Including disclosing how to correctly recognize.
- FIG. 24 is a configuration diagram of a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- the road condition monitoring system equipped with a vision sensor and a sound wave sensor includes a sound wave sensor 2410, a vision sensor 2420, an artificial neural network 2430, and a segmentation processing unit. 2440, and a control unit 2470 may be included.
- the sound wave sensor 2410 may transmit a sound wave signal to a predetermined point for road condition monitoring and then receive a reflected signal.
- the vision sensor 2420 may obtain an image of the road surface including the predetermined point.
- the artificial neural network 2430 may classify the road surface condition of the preset point based on the learned road classification model by using the reflected signal acquired by the sound wave sensor 2410 as an input signal.
- the road surface conditions may include dry, water, black ice, and snow.
- the segmentation processing unit 2440 may divide the image obtained by the vision sensor 2420 into a plurality of distinct segmentation areas based on a segmentation model as an input signal.
- the control unit 2470 controls operations of the sound wave sensor 2410, the vision sensor 2420, the artificial neural network 2430, and the segmentation processing unit 2440, and the machine output from the artificial neural network 2430.
- the road surface condition of the corresponding road may be determined by converging the road surface condition of the set point and a plurality of segmented areas output from the segmentation processing unit 2440 .
- the controller 2470 may calculate a segmentation area including a point where the sound wave sensor strikes the ground.
- image information in which a classification class (road type) of waveform data is assigned to a segmentation area including a point where the acoustic wave sensor strikes the ground (sensing area) may be output.
- 25 is a diagram illustratively illustrating recognizing a uniform road surface condition in a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- (a) is a captured image of the vision sensor 2420, and the position of the sensing area (preset area) 2500 of the acoustic sensor 2410 is indicated.
- (b) shows that the captured image of (a) is segmented and the segmented area is displayed.
- the type of road surface is classified based on the learned road surface classification model (artificial intelligence model), and the road surface condition of the detection area 2500 is detected.
- (d) shows an image where the black ice area is finally displayed by finding the segmentation area including the area 2500 detected in (c) from the segmentation areas in (b).
- the entire area of the road is divided into one segmentation area, and the sensing area 2500, which detects the road surface through the sonic sensor 2410, is detected as black ice. You can print the result.
- 26 is a diagram illustratively illustrating recognizing a non-uniform road surface condition in a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- (a) is a captured image of the vision sensor 2420, and the position of the sensing area (preset area) 2600 of the acoustic sensor 2410 is indicated.
- (b) shows that the captured image of (a) is segmented and the segmented area is displayed.
- the type of road surface is classified based on the learned road surface classification model (artificial intelligence model), and the road surface condition of the detection area 300 is detected.
- (d) shows an image where the black ice area is finally displayed by finding the segmentation area including the area 2600 detected in (c) from the segmentation areas in (b).
- the road is divided into a plurality of segmentation areas including a wet area and a dry area, and the sensing area 2600 that detects the road surface through the sonic sensor 2410 is detected as black ice, so finally The same result as (d) can be output.
- the present disclosure may include a technology capable of reliably determining, through a vision sensor, a problem regarding which part/region of a road surface image obtained by a vision sensor corresponds to road surface information accurately recognized by a sonic sensor.
- the operation of the road surface detection algorithm may be performed by periodic (minutes or seconds) or asynchronous request, and the slipperiness risk detection of the road surface acquires data through a sound wave sensor and a vision sensor, and the sound wave Based on the data obtained from the sensor, the type (state) of the road surface can be detected, and the region including the sensing part of the acoustic sensor can be detected through image segmentation in the image secured by the vision sensor.
- risk information may be combined from an image segmented as a result of segmentation and used in a form of transmitting a notification to a manager (control server) about the dangerous section of the road surface.
- FIG. 27 is a diagram for explaining a method of finding a segmentation area detected by an acoustic wave sensor in a road condition monitoring system equipped with a vision sensor and an acoustic wave sensor according to an embodiment of the present disclosure.
- the controller may determine the road surface condition of the corresponding road by converging the road surface condition of the predetermined point output from the artificial neural network and a plurality of segmented areas output from the segmentation processing unit 2440 .
- the control unit calculates the position of the midpoint of each segmented area, calculates an equation of a straight line for a plurality of line segments included in each segmented area (a plurality of line segments forming each segmented area), and For the segmented area, a first relative positive-negative relationship between the midpoint of the corresponding area and each of the plurality of line segments is determined using the equation of the straight line using the equation of the straight line, and for each segmented area, the equation of the straight line is used to determine the positive-negative relationship.
- a predetermined point and a second relative positive-yin relationship for each of the plurality of line segments may be determined, and a segmentation area in which the second relative positive-yin relationship coincides with the first relative positive-yin relationship may be determined as an area including the predetermined point. there is.
- an input RGB image is divided into a plurality of regions after being segmented, and regions A and B among them are divided as shown in the figure.
- the midpoint of area A is indicated as “2701”
- the midpoint of area B is indicated as “2702”
- the sensing area (preset point) of the acoustic wave sensor is indicated as "2700”.
- the positive-negative relationship is assumed to be the (+) direction to the right and bottom, and the (-) direction to the left and top based on the point (0,0) at the top left of the image.
- Area A is formed in the form of a pentagon, and is composed of line segments 14, 45, 56, 67, and 71.
- the positive-negative relationship between the midpoint 2701 of area A and the segments 14, 45, 56, 67, and 71 of area A is (-), (-), (-), (+), and (+), respectively. do.
- Area B is formed in a quadrangle and is composed of line segments 12, 23, 34, and 41.
- the positive-negative relationship between the detection area (preset point) 2700 of the sound wave sensor and each line segment 14, 45, 56, 67, and 71 of area A is (+), (-), (-), (+), (+), and the positive-negative relationship with respect to each line segment 12, 23, 34, and 41 in area B is (+), (-), (-), and (+), respectively.
- the sensing area (preset point) 2700 of the acoustic wave sensor is included in area B.
- FIG. 28 is a diagram for explaining an example of an artificial neural network of a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- the artificial neural network may be formed as an artificial intelligence model implemented as either a 1D Conventional Neural Network (CNN) or an Artificial Neural Network (ANN).
- CNN 1D Conventional Neural Network
- ANN Artificial Neural Network
- An input of the artificial neural network may be a reflected wave received through a sound wave sensor, and an output may be a type of road surface of a preset detection area of the sound wave sensor.
- 29 is a diagram for explaining an example of a segmentation processing unit of a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to an embodiment of the present disclosure.
- the segmentation processing unit uses an image segmentation model based on a conventional neural network (CNN) implemented by an auto-encoder or U-Net. can be formed
- An input of the segmentation processing unit is an RGB image obtained through a vision sensor, and an output is a segmentation image displaying regions classified in the corresponding image.
- FIG. 30 is a flowchart of an embodiment of a monitoring method in a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to the present disclosure.
- the reflected signal may be received (3010).
- the road surface condition of the predetermined point may be classified based on the learned road surface classification model by using the reflected signal acquired by the sound wave sensor as an input signal (3020).
- the vision sensor may obtain an image of the road surface including the predetermined point (3030).
- the image obtained by the vision sensor may be divided into a plurality of segmented regions based on a segmentation model (3040).
- condition of the road surface may be analyzed by fusing the condition of the road surface at the predetermined point and the plurality of segmented areas (3050).
- the road surface condition of the corresponding road may be determined according to the analysis of the fusion analysis step (3050) (3060).
- steps "3010" and "3030" may be periodically performed.
- a signal informing the danger may be transmitted to the control server (3080).
- the risk area may be displayed on the image including the plurality of segmented areas and transmitted to the control server.
- FIG. 31 is a detailed flowchart of an embodiment of the fusion analysis step 3050 of FIG. 30 .
- the fusion analysis step 3050 may include performing the following steps.
- the position of the midpoint of each segmented area is calculated (3051).
- a first relative positive/negative relationship between the midpoint of the corresponding area and each of the plurality of line segments is determined using the equation of the straight line (3053).
- a second relative positive/negative relationship between the predetermined point and each of the plurality of line segments is determined using the equation of the straight line (3054).
- a segmentation area where the second relative positivity relationship and the first relative positivity relationship coincide is determined as an area including the predetermined point (3055).
- FIG. 32 is a configuration diagram of a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to another embodiment of the present disclosure.
- the road condition monitoring system equipped with a vision sensor and a sound wave sensor includes a sound wave sensor 3210, a vision sensor 3220, and a first feature extraction unit 3281 , the second feature extraction unit 3282.
- a joint classifier 3290 and a controller 3270 may be included.
- the sound wave sensor 3210 may transmit a sound wave signal to a predetermined point for road condition monitoring and then receive a reflected signal.
- the vision sensor 3220 may obtain an image of the road surface including the predetermined point.
- the first feature extractor 3281 may extract a first feature from the reflected signal acquired by the acoustic wave sensor 3210 .
- the second feature extraction unit 3282 may extract a second feature from an image obtained by the vision sensor 3220 .
- the combined artificial neural network 3290 takes the first feature and the second feature as inputs and learns the road surface from features extracted from signals acquired by the sonic sensor 3210 and images acquired by the vision sensor 3220. Based on the data combination classification model, the road surface condition of the corresponding road can be classified.
- the road surface conditions may include dry, water, black ice, and snow.
- the control unit 3270 operates the sound wave sensor 3210, the vision sensor 3220, the first feature extractor 3281, the second feature extractor 3282, and the combined artificial neural network 3290. can control.
- the first feature extracted from the reflected signal and the second feature extracted from the image are learned and classified by a classification model (data combination classification model) having separate weights, respectively.
- the first feature extracted from the reflected signal and the second feature value extracted from the image can learn object (road surface type) classification with an input combination of image data and sound wave data using correlation. .
- object road surface type
- the weight and influence of the classifier based on image data and the weight and influence of the classifier based on sound wave data can be adjusted to make a final decision (prediction).
- FIG 33 is a flowchart of another embodiment of a monitoring method in a road condition monitoring system equipped with a vision sensor and a sound wave sensor according to the present disclosure.
- the reflected signal may be received (3310).
- a first feature of the reflected signal may be extracted (3320).
- the vision sensor may obtain an image of the road surface including the predetermined point (3330).
- a second feature of the image may be extracted (3340).
- the road surface condition of the corresponding road may be analyzed based on the learned classification model by combining the first feature extracted from the reflected signal and the second feature extracted from the image (3350).
- the first feature extracted from the reflected signal and the second feature extracted from the image may be learned and classified by a classification model having separate weights.
- the road surface condition of the corresponding road may be determined according to the analysis of the road surface condition analysis step (3350).
- steps "3310" and "3330" may be periodically performed.
- a signal informing the danger may be transmitted to the control server (3380).
- a danger area may be displayed on the image including the plurality of segmented areas and transmitted to the control server.
- 34 is a diagram for explaining an operation of a control system of a heating wire system for a road according to an embodiment of the present disclosure. 34 is a specific embodiment of the road infrastructure shown in FIG. 2 .
- a structure 3401 is located on the road, and the structure 3401 includes a sonic sensor 3410 and a communication unit 3420. ) and the like, and an automatic control box 3460 that controls the hot wire 3470 in the anti-icing device 3400 according to the control of the control server 3440 based on the detected data of the sonic sensor 3410 is controlled. It can be.
- the sound wave sensor 3410 may be installed on the structure 3401 so as to be located on the vehicle's driving path on the road and perpendicular to the road surface, but is not limited thereto.
- the structure 3401 means that an acoustic sensor 3410 can be installed on a road like a street light.
- the sound wave sensor 3410 may transmit a sound wave signal to a predetermined point to detect road conditions and then receive a reflected signal.
- the communication unit 3420 may transmit data acquired through the sonic sensor 3410 to the control server 3440 .
- control server 3440 may deliver a notification to the manager terminal 3450 when detecting whether the sonic sensor 3410 is out of order (abnormality).
- the hot wire method it is important how much the hot wire should be operated because a fire may occur on the asphalt by operating the hot wire excessively for a required time.
- the anti-icing device it is possible to precisely control the anti-icing device by detecting a temperature change of a road surface due to heating by a sound wave sensor.
- an artificial intelligence model learned based on sound wave sensing data accumulated in a road surface environment with various temperatures applied is created, and the acquired sound wave sensor waveform is analyzed based on the artificial intelligence model to detect the temperature change of the road surface. It is possible to automatically control the operation of the heating element.
- the heating wire is started to operate, and when the road surface temperature is maintained at 4 degrees or higher according to the output of the sound wave sensor, that is, when the temperature is higher than the freezing point of water, the heating wire can be set to stop the operation of
- the salt spray device when the salt spray device operates, it is possible to detect how much salt water is sprayed on the road surface.
- an artificial intelligence model learned based on sound wave sensing data accumulated in a road surface environment in which the degree of salt water spray is variously distributed is created, and the salt water on the road surface is analyzed by analyzing the waveform of the sound wave sensor acquired based on the artificial intelligence model.
- the sprayed (distributed) degree can be grasped.
- the salt water is distributed over a predetermined range on the road surface, it may be set to stop spraying the salt water.
- the present disclosure relates to a road surface sensing and interlocking control technology capable of timely operating a road heating system or a salt spray device that is being installed/operated, and obtains road surface information using a conventional temperature/humidity sensor mounted on a road surface. It is possible to accurately control the operation of the heating wire device or the salt water spray device by recognizing the road surface condition and determining the snow melting condition based on the sonic sensor.
- a service that can be interlocked with the existing snow melting equipment monitoring/control system in a plug-in method without major modifications, and can improve the operational efficiency of snow melting equipment based on more accurate road surface risk notification than existing snow melting systems can provide.
- the algorithm for determining whether snow melting is performed may be built in the control server (service server) 3440 or in the control unit (MCU) provided together with the sonic sensor 3410, and may be built in the freezing prevention device 3400 through the communication unit. It may be in the form of passing it to the automatic control box 3460.
- the road surface condition detection is periodically and repeatedly performed until a point in time when the acoustic sensor needs to be restored due to a failure of the acoustic sensor.
- the control server 3440 receives the reflected wave (sensor value) from the sound wave sensor 3410 and transmitting it to the control server 3440 (service server) through the communication unit, when the sensor state is normal, the control server 3440 transmits the corresponding reflected wave It analyzes using a big data-based artificial intelligence model to determine whether snow melting is currently necessary, and controls the operation of the corresponding anti-icing device.
- FIG. 35 is a block diagram of a control system of an apparatus for preventing icing on a road according to an embodiment of the present disclosure.
- the control system of FIG. 35 is a specific example of a road management device according to an embodiment of the present disclosure.
- the control system of the device for preventing icing on a road includes a sonic sensor 3510, a control server 3540, a communication unit 3520, and an device for preventing icing 3500.
- a sonic sensor 3510 can include a sonic sensor 3510, a control server 3540, a communication unit 3520, and an device for preventing icing 3500.
- a communication unit 3520 can include a sonic sensor 3510, a control server 3540, a communication unit 3520, and an device for preventing icing 3500.
- an device for preventing icing 3500 can include
- the sound wave sensor 3510 may transmit a sound wave signal to a predetermined point to detect road conditions and then receive a reflected signal.
- the control server 3540 uses the reflected signal obtained by the sound wave sensor 3510 as an input signal to detect the road surface condition data of the preset point based on the learned artificial intelligence analysis model, A signal controlling whether to operate the anti-icing device 3500 may be generated according to the road surface condition data.
- the road surface condition data may include a weather condition, a type of road surface, a temperature of the road surface, and an amount of sprayed salt (spray degree, distribution), and the like.
- the communication unit 3520 may transfer the reflected signal acquired by the acoustic wave sensor 3510 to the control server 3540 .
- the icing prevention device 3500 is controlled by the control server 3540 to perform an operation for preventing icing on the road.
- the anti-icing device 3500 may include at least one of a hot wire device and a salt spray device.
- control server 3540 determines that the weather condition is “rain” or “snow”, the classified road surface type is “wet road”, “snowy road” or “frozen road”, and the detection When the temperature of one road surface is less than 4 degrees Celsius, a control signal for operating the heating wire device is generated, and after the heating device is operated, when the detected temperature of the road surface is 4 degrees Celsius or higher, the operation of the heating wire device is controlled. It can generate a control signal to stop.
- control server 3540 determines that the weather condition is "rain” or “snow", the classified road surface type is “wet road”, “snowy road” or “frozen road”, and the detected Generating a control signal for operating the salt water spray device when the temperature of the road surface is less than 4 degrees Celsius, and operating the salt water spray device when the detected salt water injection amount is 80% or more after the salt water spray device is operated It is possible to generate a control signal to stop the
- control server 3540 transmits a notification message to the manager terminal 3550 as it detects that there is an abnormality in the state of the sonic sensor 3510, and sends the sonic sensor 3510 to the control server 3580. can deliver a status notification signal.
- 36 is a block diagram of a control system of an apparatus for preventing icing on a road according to another embodiment of the present disclosure.
- the control system of the anti-icing device on a road includes a sonic sensor 3610, a controller 3630, a communication unit 3620, and an anti-icing device 3600.
- the sound wave sensor 3610 may transmit a sound wave signal to a predetermined point to detect road conditions and then receive a reflected signal.
- the control unit 3630 uses the reflected signal obtained by the sound wave sensor 3610 as an input signal to detect road surface condition data at the preset point based on the learned artificial intelligence analysis model, and detects the road surface at the preset point.
- a signal controlling whether the freezing prevention device 3600 is operated may be generated according to the state data.
- the road surface condition data may include a weather condition, a type of road surface, a temperature of the road surface, and an amount of sprayed salt (spray degree, distribution), and the like.
- the communication unit 3620 may transfer the control signal generated by the controller 3630 to the anti-icing device 3600 .
- the icing prevention device 3600 is controlled by the control unit 3630 to perform an operation to prevent icing of the road.
- the anti-icing device 3600 may include at least one of a hot wire device and a salt spray device.
- control unit 3630 determines that the weather condition is "rain” or “snow", the classified road surface type is “wet road”, “snowy road” or “frozen road”, and the detected When the temperature of the road surface is less than 4 degrees Celsius, a control signal for operating the heating wire device is generated, and after the heating device is operated, when the detected temperature of the road surface is 4 degrees Celsius or higher, the operation of the heating wire device is stopped. It is possible to generate a control signal that
- control unit 3630 determines that the weather condition is "rain” or “snow”, the classified road surface type is “wet road”, “snowy road” or “frozen road”, and the detected road surface Generating a control signal for operating the salt spray device when the temperature of is less than 4 degrees Celsius, and controlling the operation of the salt spray device when the detected amount of salt water is 80% or more after the salt spray device is started It can generate a control signal to stop.
- control unit 3630 upon detecting that the state of the sonic sensor 3610 is abnormal, transmits a notification message to the manager terminal 3650, and the control server 3680 of the sonic sensor 3610.
- a status notification signal can be delivered.
- 37A to 37C are diagrams for explaining an artificial intelligence analysis model used in a control system of an apparatus for preventing icing on a road according to an embodiment of the present disclosure.
- the artificial intelligence analysis model includes a weather condition classification model for classifying a weather condition based on a reflected signal acquired by a sound wave sensor, and a road type classification model for classifying a road surface type based on a reflected signal acquired by a sound wave sensor.
- a weather condition classification model for classifying a weather condition based on a reflected signal acquired by a sound wave sensor
- a road type classification model for classifying a road surface type based on a reflected signal acquired by a sound wave sensor.
- the artificial intelligence analysis model learns the reflected signal obtained by the sonic wave sensor and the temperature of the road surface together, and based on the reflected signal obtained by the sonic wave sensor, the corresponding road surface temperature
- a road surface temperature regression model that outputs may be further included.
- the artificial intelligence analysis model learns the reflected signal obtained by the sound wave sensor and the temperature of the road surface together, and based on the reflected signal obtained by the sound wave sensor, the corresponding A road surface temperature regression model that outputs the temperature of the road surface, and the reflected signal obtained by the acoustic wave sensor and the injection amount (distribution degree) of salt water are learned together, and the corresponding injection amount of salt water is based on the reflected signal obtained by the sonic sensor.
- a saltwater injection amount regression model outputting may be further included.
- the artificial intelligence analysis model basically includes a weather condition classification model, a road surface type classification model, and a road surface temperature regression model, and when the anti-icing device includes the salt water injection device, a salt water injection amount regression model. may further include.
- FIG. 37A shows the structure of a road type classification model.
- the road type classification model is configured by sampling the acquisition signal (reflected wave) of the acoustic sensor a total of T times for a certain period of time and learning the corresponding road type information together.
- an acquisition signal (reflected wave) of a sound wave sensor is input and the corresponding road surface types are dry, wet, iced, and snowy. ) can be classified into classes such as
- a weather condition classification model for classifying a weather condition based on the reflected signal obtained by the acoustic wave sensor may be further included, and the acquired signal and weather information of the acoustic wave sensor may be further included. learn and construct
- FIG. 37B is a view for explaining a road surface temperature regression model for outputting a corresponding road surface temperature based on a reflected signal acquired by a sound wave sensor in order to control a heating device
- FIG. 37C is a diagram for controlling a salt water control device.
- It is a diagram for explaining a saltwater spray amount regression model that outputs the distribution amount (distribution degree) (%) of corresponding saltwater based on the reflected signal obtained by the acoustic wave sensor.
- the relationship between the acquired data (X) of the sound wave sensor and the temperature of the road surface is not a two-dimensional (plane) graph, but X is a dataset formed by the concept of a hyperplane, which is a set of values am.
- the learned road surface temperature regression model outputs a corresponding road surface temperature based on the reflected signal obtained by the acoustic wave sensor.
- the relationship between the acquisition data (X) of the acoustic sensor and the amount of salt water injection (distribution degree) is not a two-dimensional (plane) graph, but X is a concept of a hyperplane, which is a set of values. It is a dataset that is being formed.
- the learned salt water spray amount regression model outputs a corresponding spray amount (distribution degree) of salt water based on the reflected signal acquired by the acoustic wave sensor.
- 38 is a flowchart of a control method of an apparatus for preventing icing on a road according to an embodiment of the present disclosure.
- measurement data of the acoustic wave sensor is collected (3810).
- An artificial intelligence analysis model is created based on the collected data (3820).
- a weather condition classification model for classifying a weather condition is generated based on the reflected signal obtained by the sound wave sensor, and a road surface is generated based on the reflected signal obtained by the sound wave sensor.
- Creating a road surface type classification model for classifying the type of, and learning the reflected signal obtained by the acoustic wave sensor and the temperature of the road surface together to output the corresponding road surface temperature based on the reflected signal obtained by the acoustic wave sensor Create a road surface temperature regression model.
- the anti-icing device is a salt water spray device
- the artificial intelligence analysis model generating step (3820) the reflected signal acquired by the sound wave sensor and the spray amount (distribution degree) of salt water are learned together, so that the sound wave sensor Based on the obtained reflected signal, a saltwater injection amount regression model outputting the corresponding saltwater injection amount (distribution degree) is created.
- the artificial intelligence analysis model basically generates and includes a meteorological state classification model, a road surface type classification model, and a road surface temperature regression model, and when the anti-icing device includes the salt water spray device, the salt water injection amount Generates a further regression model.
- the generated artificial intelligence analysis models must be loaded into the control server or control unit.
- a sound wave signal is transmitted to a predetermined point for monitoring road conditions using the sound wave sensor, and a reflected signal is received (3830).
- control server or the control unit detects the road surface condition data of the predetermined point based on the artificial intelligence analysis model by using the received reflected signal acquired by the sound wave sensor as an input signal.
- the weather condition, the type of road surface, the temperature of the road surface, and the amount of salt spray (degree of distribution) are detected.
- control server or the control unit generates a control signal for controlling whether or not to operate the anti-icing device based on the road surface condition data (3850).
- control server or the control unit detects that there is an abnormality in the state of the acoustic wave sensor, a notification message is transmitted to the manager terminal and a state notification signal of the acoustic wave sensor is transmitted to the control server (3860).
- FIG. 39 is a detailed flowchart of one embodiment of the control signal generation step 3850 of FIG. 38 when the device for preventing icing on a road according to the present disclosure is a hot wire device.
- the anti-icing device is a hot wire device
- the control signal generating step (3850) first, it is determined whether the detected meteorological condition is "rain” or "snow” (3910).
- step 3910 if the meteorological condition is not “rain” or “snow”, the process proceeds to step 3840 to detect road condition data.
- the classified road type is “wet” or “snow” or “frozen road”. (iced)" (3920).
- step 3920 if the weather condition is “rain” or “snow”, the classified road surface type is “wet” or “snow” or “iced road”. )", it proceeds to step "3840" to detect road condition data.
- the classified road type is “wet” or “snow” or “frozen road”. (iced)”, it is determined whether the detected road surface temperature is less than 4 degrees Celsius (3930).
- step 3930 if the temperature of the road surface is not less than 4 degrees Celsius, the process proceeds to step "S540" to detect road condition data.
- the road condition data detection step 3940 is performed, and the road surface condition data is sensed.
- the heating element After the heating element is operated, it is determined whether the detected temperature of the road surface is 4 degrees Celsius or higher (3950).
- step 3950 if the temperature of the road surface is not higher than 4 degrees Celsius, the process proceeds to step "S540" to detect road condition data.
- the road condition data detection step 3840 is performed to sense the road condition data.
- the weather condition is "rain” or “snow”
- the classified road type is “wet road”, “snowy road” or “frozen road”
- the detected temperature of the road surface is less than 4 degrees Celsius.
- the heating wire device is operated, and after the heating wire device is operated, the operation of the heating wire device is stopped when the detected temperature of the road surface is 4 degrees Celsius or higher.
- FIG. 40 is a detailed flowchart of one embodiment of the control signal generation step 3850 of FIG. 38 when the device for preventing icing on a road according to the present disclosure is a salt water spray device.
- the road freezing prevention device is a salt spray device
- the control signal generating step (3850) first, it is determined whether the detected meteorological condition is "rain” or "snow” (4010).
- step 4010 if the meteorological condition is not "rain” or "snow", the process proceeds to step "S540" to detect road condition data.
- the classified road type is "wet” or “snow” or “frozen road”. (iced)" (4020).
- step 4020 if the weather condition is "rain” or “snow”, the classified road type is “wet” or “snow” or “iced”. )", it proceeds to step "3840" to detect road condition data.
- the classified road type is “wet” or “snow” or “frozen road”. (iced)”, it is determined whether the detected road surface temperature is less than 4 degrees Celsius (4030).
- step 4030 if the temperature of the road surface is not less than 4 degrees Celsius, the process proceeds to step "3840" to detect road condition data.
- step 4030 if the temperature of the road surface is less than 4 degrees Celsius, a control signal for operating the salt spray device is generated (4040).
- the road surface condition data detection step 3840 is performed, and the road surface condition data is sensed.
- the spray amount (spray degree) is 80% or more (4050).
- step 4050 if the spray amount (degree of spray) of salt water is not 80% or more, the process proceeds to step 3840 to detect road surface condition data.
- the road condition data detection step 3840 is performed to sense the road condition data.
- the weather condition is "rain” or “snow”
- the classified road type is “wet road”, “snowy road” or “frozen road”
- the temperature of the detected road surface is less than 4 degrees Celsius.
- the salt spray device is operated, and after the salt spray device is operated, the operation of the salt spray device is stopped when the detected amount of salt spray is 80% or more.
- the amount of salt spraying (degree of spraying, distribution) for stopping the operation of the salt spraying device is 80% or more, but it is not limited thereto.
- a device for preventing icing on the road including a heating wire device or a salt spray device
- a salt spray device has been cited as an example, but the present disclosure is not limited thereto, and it is also possible to control a system including a heat wire device and a salt spray device.
- the methods according to the embodiments of the present disclosure can be implemented by a computer-readable recording medium in which a program for implementing the method is stored and/or a program stored in a computer-readable recording medium for implementing the method.
- a program of instructions for implementing the methods according to the embodiments of the present disclosure may be provided in a computer-readable recording medium by being tangibly implemented. In other words, it may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable recording medium.
- the computer readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.
- a computer readable storage medium storing one or more programs (software modules) may be provided.
- One or more programs stored in a computer-readable storage medium are configured for execution by one or more processors in an electronic device.
- One or more programs include instructions that cause the electronic device to execute methods according to embodiments described in the claims or specification of the present disclosure.
- Such programs may include random access memory, non-volatile memory including flash memory, read only memory (ROM), and electrically erasable programmable ROM.
- EEPROM Electrically Erasable Programmable Read Only Memory
- magnetic disc storage device Compact Disc-ROM (CD-ROM), Digital Versatile Discs (DVDs), or other forms of It can be stored on optical storage devices, magnetic cassettes. Alternatively, it may be stored in a memory composed of a combination of some or all of these. In addition, each configuration memory may be included in multiple numbers.
- the program accesses through a communication network such as the Internet, an Intranet, a Local Area Network (LAN), a Wide LAN (WLAN), or a Storage Area Network (SAN), or a communication network consisting of a combination thereof. It can be stored on an attachable storage device that can be accessed. Such a storage device may be connected to a device performing an embodiment of the present disclosure through an external port. In addition, a separate storage device on a communication network may be connected to a device performing an embodiment of the present disclosure.
- a communication network such as the Internet, an Intranet, a Local Area Network (LAN), a Wide LAN (WLAN), or a Storage Area Network (SAN), or a communication network consisting of a combination thereof. It can be stored on an attachable storage device that can be accessed.
- Such a storage device may be connected to a device performing an embodiment of the present disclosure through an external port.
- a separate storage device on a communication network may be connected to a device performing an embodiment of the present disclosure.
- FIGS. 2, 23, and 34 a method of installing the road infrastructure of the present disclosure on a road will be described by way of example. More specifically, the structure in the following description is the structure of FIGS. 2, 23, and 34, and relates to the structure and installation method of the structure of the present disclosure.
- FIGS. 41 to 49 illustrating an embodiment of the present disclosure.
- the structure 4100 which is the main component of the road infrastructure sensor construction structure of the present disclosure, includes: a vertical frame 4110 erected and installed on a road or the edge of the road, and the vertical frame 4110 It is configured to include a horizontal frame 4120 installed in the width direction of the road at the top, for example, a "c"-shaped structure or high-pass IC for installing a "c"-shaped street light or electronic display board. It may be a structure, and any structure may be used as long as the horizontal frame 4120 is located at the top of the road. can be located As described above, the position of the acoustic sensor unit of the present disclosure is illustrative and is not limited to the position described in the present disclosure.
- the acoustic wave sensor unit 4200 which is a major component of the road infrastructure sensor construction structure of the present disclosure, is installed below the horizontal frame 4120 of the structure 4100, It is installed to be located at the top, irradiates sound waves on the road surface, receives sound waves reflected from the road surface to generate sound wave information, and transmits the received sound wave information to the control unit 4300, which will be described in detail later.
- the control unit 4300 converts the sound wave information into a frequency so that the condition of the road surface can be grasped.
- the sound wave sensor unit 4200 of the present disclosure transmits a sound wave signal to the road surface, receives the reflected sound wave signal, and outputs an outgoing signal under the control of the control unit 4300, and the outgoing signal is random. It may be configured to include a receiver for receiving a reflected signal that is reflected on the road surface and returned.
- the transmitter and the receiver are positioned so that the sound wave is transmitted in a straight line and the reflected sound wave is received. It is expressed as consisting of
- a plurality of sound wave sensor units 4200 are used.
- the sound wave sensor unit 4200 composed of a first transmission/reception member 4250 and a second transmission/reception member 4260 capable of mutually receiving transmitted and reflected sound wave signals with one embodiment configured, conventionally Compared to this, it is possible to grasp the road surface condition of a relatively wide road, so that the condition of the road can be estimated with high reliability.
- the sound wave sensor unit 4200 of one embodiment is installed below the horizontal frame 4120 of the structure 4100, and as a plurality of them are installed in the width direction of the road, the state of the road surface is wider than before. Therefore, it is possible to obtain the effect of improving the reliability of identifying the condition of the road surface.
- the plurality of sensor units 4200 installed in one embodiment are characterized in that the transmission times of the sound waves are set so that the arrival times of the sound waves irradiated and reflected on the road surface are all the same, which is Not only are the heights different, but the arrival times of sound waves reflected by variables such as breakage can all be different, so the characteristics of sound waves in normal road conditions, which are the initial standard, are extracted and compared to be relatively similar, so that each sound wave transmission time is set. This is to make the arrival time the same, so that the condition of the road surface can be quickly identified.
- the reason for setting the transmission time of the sound wave to make the arrival time the same is because when sound wave information is generated using the sound wave transmission time and arrival time, a plurality of sound wave sensor units 4200 of the same equipment are installed. In this case, since the velocity of the sound wave is the same, if the transmission times are all the same due to variables such as the height of the road surface, the arrival times of the reflected sound waves are all different, so it is necessary to analyze the sound wave information generated by each sound wave sensor unit 4200.
- the transmission time of the sound waves of the plurality of sound wave sensor units 4200 according to the height of the road surface is set to make the arrival time the same, when the road surface is in a normal state, the arrival time of the sound wave is all the same, and the road surface
- the state of the road is in a state such as damage or black ice
- the arrival time of the sound wave is different from the preset arrival time of the sound wave, so it is easy to determine that the state of the entire road surface is different, but the arrival of some of the plurality of sound wave sensor units 4200 When the time is different from the predetermined arrival time of the sound wave, it is possible to more quickly check that the state of a part of the entire road surface is different.
- the plurality of sound wave sensor units 4200 of one embodiment is a time when sound waves are transmitted from any one sound wave sensor unit 4200 and reflected on the road surface, that is, when the sound wave flight period is t, t / 2 time Characterized in that n sensors transmit sound waves to the road surface more than n times sequentially and receive reflected sound waves for the remaining t/2 time to sample road surface information or traffic volume information n times or more comprehensive road information within a predetermined period.
- the sound wave sensor unit 4200 of one embodiment can sense the condition of the road surface with improved reliability by sampling and generating a larger amount of sound wave information such as road surface information and traffic information through a plurality of sound wave sensor units 4200. to realize the effect of At this time, it will be apparent that the sound wave sensor unit 4200 of another embodiment, which will be described in detail later, also samples and generates sound wave information such as road surface information and traffic information through sound waves.
- the sound wave sensor unit 4200 of one embodiment is coupled bundle 4210, the upper portion of which is coupled to the lower portion of the horizontal frame 4120 of the structure 4100, and the upper portion of the lower portion of the coupling bundle 4210 is front and rear and Consisting of a connecting rod 4220 hinged to be rotatable in the left and right directions, a main body 4230 coupled to the lower end of the connecting rod 4220, and an acoustic sensor 4240 installed below the main body 4230 do.
- the front-and-back direction means the longitudinal direction of the road
- the left-right direction means the width direction of the road
- the front-and-back and left-right directions (lateral directions) mentioned later also mean the same direction.
- the coupling bundle 4210 is composed of a lower receiving groove 4212 formed at the bottom and a ball bearing installed inside the lower receiving groove 4212, and the connecting rod 4220 is at the upper end of the coupling bundle ( 4210) is coupled in the form of a ball hinge so as to be rotatable in the front and rear and left and right directions as configured to include an upper sphere 4224 that is inserted into and coupled to the inner side of the lower receiving groove 4212.
- the lower receiving groove 4212 is formed in a shape corresponding to the upper sphere 4224 of the connecting rod 4220, and the connecting rod 4220 has an upper portion of the lower part of the coupling bundle 4210. It is combined with a hinge structure and is rotatable in the front and rear and left and right directions, so that shaking is prevented when vibration is generated in the structure 4100 due to vehicle traffic and external vibration.
- the main body 4230 coupled to the lower end of the connecting rod 4220 and the sonic sensor 4240 installed below the main body 4230 are prevented from shaking together as the connecting rod 4220 is prevented from shaking.
- An effect of enabling the sound wave to be irradiated to the road surface set in the sound wave sensor 4240 to be stably irradiated can be obtained.
- the main body 4230 has a sound wave sensor 4240 stably installed in the sound wave sensor unit 4200 of the temporary embodiment and the sound wave sensor unit 4200 of another embodiment to be described in detail later, and the control unit 4300 to be described in detail later
- the sound wave sensor 4240 is composed of a transmitter and a receiver to irradiate sound waves on the road surface and receive reflected sound waves to receive sound waves. Information is generated, and the generated sound wave information is transmitted to the control unit 4300.
- the sound wave sensor unit 4200 of another embodiment is installed on one lower side of the horizontal frame 4120 of the structure 4100 to irradiate or receive sound waves on the road surface of the road.
- a first transmission/reception member 4250 It is installed on the lower side of the horizontal frame 4120 of the structure 4100 and includes a second transmission/reception member 4260 for irradiating or receiving sound waves on the road surface.
- the first transmission/reception member 4250 is installed at an angle capable of receiving the sound wave reflected from the second transmission/reception member 4260 on the road, and the second transmission/reception member 4260 is the first transmission/reception member 4260. It is characterized in that the member 4250 is installed at an angle capable of receiving reflected sound waves irradiated onto the road.
- either the first transmission/reception member 4250 or the second transmission/reception member 4260 transmits sound waves to the road surface, and transmits the reflected sound waves to the second transmission/reception member 4260.
- the other sound wave transmission unit is used to detect the road surface condition. It realizes the effect that can be grasped smoothly.
- the sound wave sensor unit 4200 of another embodiment adjusts the angle of any one of the first transmission/reception member 4250 and the second transmission/reception member 4260, and receives the sound wave according to the adjusted angle.
- the transmission/reception member 4260 or the first transmission/reception member 4250 it is possible to grasp the condition of a wider road surface than in the prior art.
- the horizontal frame 4120 of the structure 4100 for installing the sound wave sensor unit 4200 is a first rail 4122 installed in the longitudinal direction at the lower front and a rotation motor 4126 coupled to the first rail 4122 and controlled by the controller 4300 to rotate the first rail 4122 .
- the sound wave sensor unit 4200 of Example 1 of another embodiment that is, the first transmission/reception member 4250 and the second transmission/reception member 4260 are installed on one side and the other side of the first rail 4122, so that the first rail ( A coupling bundle 4210 that moves in opposite directions according to the rotation of 4122, a connecting rod 4220 coupled to the lower portion of the coupling bundle 4210 so that the upper portion can rotate in the front and rear and left and right directions, and the connecting rod 4220 )
- It is configured to include a sound wave sensor 4240 that is rotated in the width direction of the road by the driving motor 4270 and the angle is adjusted.
- the sound wave sensor unit 4220 of Example 1 of another embodiment receives the sound waves of the road surface area of the initially set road, and controls the control unit 4300 to transmit and receive signals between the first transmission/reception member 4250 and the second transmission/reception member 4260.
- the control unit 4300 controls the control unit 4300 to transmit and receive signals between the first transmission/reception member 4250 and the second transmission/reception member 4260.
- the coupling relationship between the first rail 4122 and the coupling bundle 4210 is that the direction of the screw thread is formed differently on one side and the other outer periphery of the first rail 4122, and the coupling bundle 4210 has the first One side and the other side of the first rail 4122 are penetrated and screwed together, so that the coupling bundle 4210 moves in a lateral direction, that is, one side or the other side along the first rail 4122 rotated by the rotation motor 4126. It is moved, and a pair of coupling bundles 4210 are moved in opposite directions along the threads formed on the outer periphery of both sides of the first rail 4122.
- the horizontal frame 4120 of the structure 4100 for installing the sound wave sensor unit 4200 is a first rail 4122 installed in the longitudinal direction at the lower front. ), and a second rail 4124 installed in the longitudinal direction at the rear of the lower part and coupled to the first rail 4122 and the second rail 4124, respectively, and controlled by a control unit 4300 to be described in detail later It is configured to include a rotation motor 4126 that rotates the first rail 4122 and the second rail 4124.
- the sound wave sensor unit 4200 of Example 2 of another embodiment that is, the first transmission/reception member 4250 and the second transmission/reception member 4260 are respectively attached to either the first rail 4122 or the second rail 4124.
- a coupling bundle 4210 installed and moved according to the rotation of the first rail 4122 or the second rail 4124, a main body 4230 installed under the coupling bundle 4210, and the main body 4230 ) installed in the lower part of the drive motor 4270 controlled by the control unit 4300 and installed in the lower part of the drive motor 4270 and rotated in the width direction of the road by the drive motor 4270 at an angle
- It is configured to include a sound wave sensor 4240 that is controlled.
- the sound wave sensor unit 4200 of Example 2 of another embodiment receives the sound waves of the road surface area of the initially set road, and the first transmission/reception member 4250 by the control unit 4300
- the control unit 4300 By adjusting the angle and the position of the second transmission/reception member 4260 in the road width direction, it is possible to receive sound waves in a road surface area other than the initially set road surface area, so that the condition of a road surface that is wider than before can be grasped.
- the effect of improving the reliability of the status identification can be obtained.
- the coupling relationship between the first rail 4122, the second rail 4124, and the coupling bundle 4210 is that a screw thread is formed on the outer periphery of the first rail 4122 and the second rail 4124, and the The first rail 4122 and the second rail 4124 are penetrated and screwed into the coupling bundle 4210, so that the first rail 4122 and the second rail 4124 rotated by the rotation motor 4126 Along the lateral direction, that is, the coupling bundle 4210 is moved in one or the other direction.
- the coupling relationship between the drive motor 4270 and the sonic sensor 4240 of the first and second embodiments of the other embodiments is that the drive motor 4270 rotates left and right according to the operation and the sonic sensor 4240 is a gear
- the driving motor 4270 is controlled by a control unit 4300 coupled through a box 4280 and described in detail later, so that the installed angle of the acoustic sensor 4240 is adjusted.
- first transmission and reception member 4250 and the second transmission and reception member 4260 of the embodiment 1 and embodiment 2 of the other embodiment may be configured to include a connecting rod 4220 rotatably hinged in the front and rear and left and right directions.
- the first transmission/reception member 4250 and the second transmission/reception member 4250 and the second transmission/reception member 4260 of Examples 1 and 2 of the other embodiments have an upper portion at the bottom of the coupling bundle 4210 in the front-back and left-right directions. It is configured to include a connecting rod 4220 coupled to be rotatable, and the main body 4230 of the first transmission/reception member 4250 and the second transmission/reception member 4260 is coupled to the lower end of the connecting rod 4220, It has the same structure as the structure of the coupling bundle 4210 and the connecting rod 4220 and the main body of the acoustic sensor unit 4200 of the embodiment. At this time, the coupling bundle 4210 and the connecting rod 4220 are configured in the same manner as in the sound wave sensor unit 4200 of the previous embodiment.
- the sound wave sensor units 4200 of the first and second embodiments that is, the first transmission and reception member 4250 and the second transmission and reception member 4260 of other embodiments, also vibrate the structure 4100 by the connecting rod 4220.
- shaking of the connecting rod 4220, the main body, and the sound wave sensor 4240 is prevented, so that sound waves can be irradiated and received more stably.
- the main body 4230 of Examples 1 and 2 of one embodiment and another embodiment includes an upper receiving groove 4234 formed on the upper portion and a ball bearing installed inside the upper receiving groove 4234, , and the connecting rod 4220 may include a lower sphere 4226 inserted into the upper receiving groove 4234 of the main body 4230 and coupled to the lower end. Accordingly, the main body 4230 ) is coupled to the connecting rod 4220 in the form of a ball hinge so as to be rotatable in the front and rear and left and right directions to prevent shaking secondarily, so that sound waves can be transmitted and received from the sound wave sensor 4240 more stably.
- connecting rods 4220 of Example 1 and Example 2 of one embodiment and other embodiments are coupled to the upper outer periphery, coupled so that the center penetrates, and is located on the upper part of the sonic sensor 4240, and the center is the upper part. It is formed in a circular shape with a convex curved surface and has an open lower portion, and includes a protective member 4222 having a reflective layer 4222a capable of reflecting sound waves on the inner surface.
- the protective member 4222 is coupled so that the connecting rod 4220 passes through the center and is positioned above the sonic sensor 4240, so that the sound wave signal reflected from the road surface is transmitted to the sonic sensor 4240. Even if it is not directly received, it is reflected and received by the reflective layer 4222a so that as many sound wave signals as possible can be received.
- the protective member 4222 protects the upper part of the acoustic wave sensor 4240 to minimize damage to the acoustic wave sensor 4240 caused by ultraviolet rays or rainwater or interference with receiving sound waves due to bird droppings. .
- the main body 4230 is configured to include a plurality of auxiliary receiving sensors 4232 installed thereon.
- the auxiliary receiving sensor 4232 is the protective member ( Since sound waves reflected by the reflective layer of 4222 are difficult to be received by the main body 4230 located above the sound wave sensor 4240, the reflected sound waves can be more stably received.
- rotation motors 4126 of the first and second embodiments of the other embodiments are coupled by connecting rotation rods to the first rail 422 and the second rail 4124, respectively, and the horizontal frame 4120 The upper part is fixedly coupled to the lower part.
- the control unit 4300 varies the frequency of the sound wave every predetermined time and irradiates it.
- this enables the generation of sound wave information capable of determining the condition of the road surface in more detail through different frequencies, thereby obtaining an effect of identifying the condition of the road surface with higher reliability.
- the sound wave sensor unit 4200 of one embodiment and another embodiment of the present disclosure irradiates a road surface with a sound wave of 40 kHz normally, and when a predetermined time is reached, the controller 4300 irradiates a sound wave of 80 kHz to the road surface, , When the preset time is reached again, the control unit 4300 irradiates 120 kHz sound waves to the road surface so that sound wave information capable of determining a more detailed road surface condition can be generated.
- the sound wave sensor unit 4200 of one embodiment and another embodiment of the present disclosure irradiates a sound wave on the road surface
- the frequency of the sound wave is irradiated differently for each predetermined time, but irradiated over a predetermined number of n times,
- the control unit 4300 which is a major component of the road infrastructure sensor construction structure of the present disclosure, is installed in the vertical frame 4110 of the structure 4100, receives sound wave information from the sound wave sensor unit 4200, and receives sound wave information from the central management server. Specifically, the characteristics of the sound wave signal are extracted from the sound wave information received from the sound wave sensor 4240, classified, and the condition of the road surface is grasped, and then the condition of the road surface is estimated, and the estimated road surface condition is transmitted to By transmitting to the central management server, it is possible to take measures to prevent accidents caused by the current state of the road surface.
- the control unit 4300 of the present disclosure not only controls the sound wave sensor 4240 described above, but also automatically controls the rotation motor 4126 and the drive motor 4270 with preset input values, or input information of the central management server. controlled by
- control unit 4300 of the present disclosure includes a signal converter that obtains a frequency domain signal by performing frequency conversion on a preset area on the domain of sound wave information received from the sound wave sensor 4240, and converting the frequency domain signal into an input signal. It can be configured to include an artificial neural network that extracts and classifies the characteristics of the input signal based on the learned road surface classification model and estimates the state of the road surface, and controls them.
- control unit 4300 of the present disclosure may be included in a switchboard or terminal box and installed in the vertical frame 4110 of the structure 4100, and may be a wired or wireless communication unit to transmit sound wave information to the central management unit server.
- the construction method of the road infrastructure sensor construction structure of the present disclosure includes a structure installation step (4S10) of installing the structure 4100 on the road, and a sensor installation step (4S20) of installing the sound wave sensor unit 4200 to the structure 4100. and a terminal box installation step (4S30) of installing the control unit 4300 in the structure 4100.
- the vertical frame 4110 is erected and installed on a road or the edge of the road, and the horizontal frame 4120 is coupled to the top of the vertical frame 4110 in the width direction of the road to form the vertical frame.
- a structure 4100 including a 4110 and a horizontal frame 4120 is installed.
- the structure 4100 has a "L" shape like the street lamp shown in FIGS. 41 to 44, it is installed in the same way as above and has a "c" shape like the billboard structure shown in FIGS. 45 to 48
- a pair of vertical frames 4110 are erected and installed, and a horizontal frame 4120 connecting the upper portions of the pair of vertical frames 110 is installed.
- the structure installation step 4910 of the present disclosure may be omitted because it is performed in advance when a structure 4100 such as a street lamp or an electronic display board structure is already installed.
- the sound wave sensor unit 4200 which generates sound wave information by receiving reflected sound waves after irradiating sound waves on the road surface, is installed on the horizontal frame of the structure 4100. (4120), the coupling bundle 4210 described above is installed at the bottom of the horizontal frame 4120.
- the coupling bundle 4210 is fixedly coupled to the lower portion of the horizontal frame 4120 when the sound wave sensor unit 4200 of one embodiment is installed, and the horizontal frame when the sound wave sensor unit 4200 of another embodiment is installed ( It is movably installed on the first rail 4122 and the second rail 4124 installed under the 4120, respectively.
- the coupling bundle 4210 includes a connecting rod 4220 coupled to the lower portion when the sonic sensor unit 4200 of one embodiment is installed, a protective member 4222 installed on the outer periphery of the connecting rod 4220, and the connecting rod Includes a main body 4230 coupled to the lower part of the main body 4220, a plurality of auxiliary receiving sensors 4232 coupled to the upper part of the main body 4230, and a sound wave sensor 4240 coupled to the lower part of the main body 4230 Or, when the sonic sensor unit 4200 of another embodiment is installed, the connecting rod 4220 coupled to the lower part, the protective member 4222 installed on the outer periphery of the connecting rod 4220, and the lower part of the connecting rod 4220 A main body 4230 coupled to the main body 4230, a plurality of auxiliary receiving sensors 4232 coupled to the upper portion of the main body 4230, a driving motor 4270 coupled to the lower portion of the main body 4230, and the driving motor 4270 ) This is a state in which the acoustic wave sensor
- the vertical frame 4110 of the structure 4100 is connected to the sound wave sensor unit 4200, and the control unit is connected to the central management server by wire or wirelessly.
- the control unit is connected to the central management server by wire or wirelessly.
- the sound wave transmission time is set so that all arrival times of sound waves that are reflected and received by the plurality of sound wave sensor units 4200 are the same.
- the initial transmission setting step of setting the first transmission/reception member 4250 and the second transmission/reception member 4260 to receive mutually transmitted sound waves It consists of more.
- the road infrastructure sensor system construction structure and its construction method of the present disclosure not only can smoothly grasp the condition of the road surface without contact through sound waves, but also the condition of the road surface according to the grasp of the condition of the road surface by a wider measurement range than in the prior art. It is possible to improve the reliability of estimation, and by allowing many sound waves to be received through the protective member 4222 on which the reflection layer 4222a is formed, the problem of receiving even a small disturbance due to the nature of sound waves having linearity is difficult to increase, thereby increasing the reliability of measurement by sound waves.
- the vibration of the sound wave sensor unit 4200 is minimized through the ball hinge structure and at the same time, the natural frequency generated by the vibration of the structure 4100 is a protective member. By minimizing what is received through 4222, it is possible to obtain an effect of improving higher measurement reliability by minimizing measurement errors.
- drawings describing the method of the present disclosure may omit some components and include only some components within a range that does not impair the essence of the present disclosure.
- the method of the present disclosure may be executed by combining some or all of the contents included in each embodiment within the scope of not detracting from the essence of the disclosure.
Landscapes
- Engineering & Computer Science (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Automation & Control Theory (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Emergency Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Traffic Control Systems (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
Description
Claims (15)
- 음파 신호를 이용하여 노면을 분류하는 전자 장치에 있어서,음파 신호를 송신하고 수신하도록 설정된 송수신기;대기 센서; 및상기 송수신기 및 상기 대기 센서와 전자적으로 연결된 적어도 하나의 프로세서를 포함하고,상기 적어도 하나의 프로세서는,상기 송수신기를 이용하여, 상기 전자 장치로부터 제1 거리만큼 이격된 대상 노면을 향해 음파 신호를 송신하고,상기 송수신기를 이용하여, 상기 대상 노면에 대한 상기 음파 신호의 반사 신호를 수신하고,상기 대기 센서를 이용하여, 상기 음파 신호와 연관된 대기 정보를 획득하고,상기 수신된 반사 신호에 대한 제1 데이터를 획득하고,상기 대기 정보에 기초하여 상기 제1 데이터를 보정함으로써, 제2 데이터를 생성하고,상기 제2 데이터에 기초하여 상기 제2 데이터의 주파수 도메인 정보와 관련된 제3 데이터를 획득하고,상기 제3 데이터 및 노면 분류 인공 신경망에 기초하여 상기 대상 노면의 종류를 판단하도록 설정되고,상기 노면 분류 인공 신경망은 상기 제1 거리와는 다른 제2 거리의 노면에서 반사된 음파 신호에 기초하여 생성된 주파수 도메인 데이터 셋으로 학습되는 것을 특징으로 하는, 전자 장치.
- 제1 항에 있어서,상기 제2 데이터는, 상기 대기 정보 및 상기 제1 거리에 기초하여 상기 제1 데이터를 보정함으로써 생성되는 것을 특징으로 하는, 전자 장치.
- 제1 항에 있어서,상기 제1 거리는, 상기 음파 신호의 송신 시점 및 상기 반사 신호의 수신 시점에 기초하여 추정되는 것을 특징으로 하는, 전자 장치.
- 제1 항에 있어서,상기 제3 데이터는 상기 제2 데이터를 STFT(Short-Time Fourier Transformation) 변환하여 획득되는 것을 특징으로 하는, 전자 장치.
- 제1 항에 있어서,상기 적어도 하나의 프로세서는,상기 판단된 대상 노면의 종류에 기초하여, 상기 대상 노면에 설치된 노면 관리 장치를 제어하는 신호를 생성하도록 설정되고,상기 노면 관리 장치는, 열선 또는 염수 분사 장치를 포함하는 것을 특징으로 하는, 전자 장치.
- 제5 항에 있어서,상기 적어도 하나의 프로세서는,미리 설정된 기상 조건의 만족 여부를 판단하고,상기 미리 설정된 기상 조건을 만족하는 경우, 상기 노면 관리 장치를 제어하는 신호를 생성하되,제1 시점에서 판단된 대상 노면의 종류가 제2 시점에서 변경되었는지 여부를 확인하고,상기 제1 시점에서 상기 대상 노면의 종류로 판단된 제1 클래스와 상기 제2 시점에서 상기 대상 노면의 종류로 판단된 제2 클래스가 서로 다른 경우, 제3 시점에서 판단되는 대상 노면의 종류에 기초하여 상기 대상 노면에 설치된 장치에 대한 제어 신호의 생성 여부를 결정하도록 설정되는 것을 특징으로 하는, 전자 장치.
- 제1 항에 있어서,상기 대상 노면의 종류는 제1 주기마다 판단되고,상기 적어도 하나의 프로세서는,상기 대상 노면의 종류가 제1 클래스로 판단되는 경우, 상기 대상 노면의 종류를 제2 주기마다 판단되도록 설정되는 것을 특징으로 하는, 전자 장치.
- 제1 항에 있어서,상기 전자 장치는 상기 대상 노면의 온도 정보를 획득하는 IR 센서 또는 상기 대상 노면의 영상 정보를 획득하는 비전 센서 중 적어도 하나를 더 포함하고,상기 적어도 하나의 프로세서는, 상기 온도 정보 또는 상기 영상 정보에 더 기초하여 상기 대상 노면의 종류를 판단하도록 설정되는 것을 특징으로 하는, 전자 장치.
- 전자 장치에 의해 수행되는 음파 신호를 이용하여 노면을 분류하는 방법에 있어서,상기 전자 장치로부터 제1 거리만큼 이격된 대상 노면을 향해 음파 신호를 송신하는 단계;상기 대상 노면에 대한 상기 음파 신호의 반사 신호를 수신하는 단계;상기 음파 신호와 연관된 대기 정보를 획득하는 단계;상기 수신된 반사 신호에 대한 제1 데이터를 획득하는 단계;상기 대기 정보에 기초하여 상기 제1 데이터를 보정함으로써, 제2 데이터를 생성하는 단계;상기 제2 데이터에 기초하여 상기 제2 데이터의 주파수 도메인 정보와 관련된 제3 데이터를 획득하는 단계; 및상기 제3 데이터 및 노면 분류 인공 신경망에 기초하여 상기 대상 노면의 종류를 판단하는 단계를 포함하고,상기 노면 분류 인공 신경망은 상기 제1 거리와는 다른 제2 거리의 노면에서 반사된 음파 신호에 기초하여 생성된 주파수 도메인 데이터 셋으로 학습되는 것을 특징으로 하는, 방법.
- 제9 항에 있어서,상기 제2 데이터를 생성하는 단계는, 상기 대기 정보에 기초하여 보정된 상기 제1 데이터를 상기 제1 거리에 기초하여 보정하는 단계를 더 포함하는 것을 특징으로 하는, 방법.
- 제9 항에 있어서,상기 음파 신호의 송신 시점 및 상기 반사 신호의 수신 시점에 기초하여 상기 제1 거리를 추정하는 단계를 더 포함하는 것을 특징으로 하는, 방법.
- 제9 항에 있어서,상기 제3 데이터는 상기 제2 데이터를 STFT(Short-Time Fourier Transformation) 변환하여 획득되는 것을 특징으로 하는, 방법.
- 제9 항에 있어서,상기 판단된 대상 노면의 종류에 기초하여, 상기 대상 노면에 설치된 노면 관리 장치를 제어하는 신호를 생성하는 단계를 더 포함하고,상기 노면 관리 장치는 열선 또는 염수 분사 장치를 포함하는 것을 특징으로 하는 것을 특징으로 하는, 방법.
- 제13 항에 있어서,상기 노면 관리 장치를 제어하는 신호를 생성하는 단계는,미리 설정된 기상 조건의 만족 여부를 판단하는 단계;상기 미리 설정된 기상 조건을 만족하는 경우, 제1 시점에서 판단된 대상 노면의 종류가 제2 시점에서 변경되었는지 여부를 확인하는 단계; 및상기 제1 시점에서 상기 대상 노면의 종류로 판단된 제1 클래스와 상기 제2 시점에서 상기 대상 노면의 종류로 판단된 제2 클래스가 서로 다른 경우, 제3 시점에서 판단되는 대상 노면의 종류에 기초하여 상기 대상 노면에 설치된 장치에 대한 제어 신호의 생성 여부를 결정하는 단계를 포함하는 것을 특징으로 하는, 방법.
- 제9 항에 있어서,상기 대상 노면의 종류를 판단하는 단계는, 상기 대상 노면의 온도 정보 또는 상기 대상 노면의 영상 정보에 더 기초하여 상기 대상 노면의 종류를 판단하는 단계를 포함하고,상기 대상 노면의 종류는 제1 주기마다 판단되고,상기 대상 노면의 종류가 제1 클래스로 판단되는 경우, 상기 대상 노면의 종류는 제2 주기마다 판단되는 것을 특징으로 하는, 방법.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CA3229412A CA3229412A1 (en) | 2021-11-17 | 2022-11-11 | A device and method for estimating and managing road surface types using sound signals. |
CN202280076362.1A CN118265994A (zh) | 2021-11-17 | 2022-11-11 | 使用声音信号估计和管理路面类型的装置和方法 |
EP22895965.6A EP4435706A1 (en) | 2021-11-17 | 2022-11-11 | Apparatus for estimating type of and managing road surface using sound wave signal, and method therefor |
US18/439,766 US20240183117A1 (en) | 2021-11-17 | 2024-02-13 | Device and method for estimating and managing road surface types using sound signals |
Applications Claiming Priority (20)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2021-0158459 | 2021-11-17 | ||
KR10-2021-0158479 | 2021-11-17 | ||
KR1020210158459A KR102397312B1 (ko) | 2021-11-17 | 2021-11-17 | 음파의 도메인 변환을 이용한 노면 종류 추정 장치 및 그 방법 |
KR1020210158464A KR102505159B1 (ko) | 2021-11-17 | 2021-11-17 | 음파를 이용한 노면 종류 추정 장치 및 그 방법 |
KR10-2021-0158464 | 2021-11-17 | ||
KR1020210158479A KR102415195B1 (ko) | 2021-11-17 | 2021-11-17 | 대기 감쇄량이 보정된 음파를 이용한 노면 종류 추정 장치 및 그 방법 |
KR10-2022-0089330 | 2022-07-20 | ||
KR1020220089331A KR102615591B1 (ko) | 2022-07-20 | 2022-07-20 | 음파 신호를 이용한 도로 정보 수집 장치 및 그를 이용한 노면 관리 방법 |
KR1020220089330A KR20240012630A (ko) | 2022-07-20 | 2022-07-20 | 복수의 음파 신호를 이용한 노면 상태 변경을 감지하는 장치 및 그 방법 |
KR10-2022-0089329 | 2022-07-20 | ||
KR1020220089329A KR20240012629A (ko) | 2022-07-20 | 2022-07-20 | 음파 신호를 이용한 노면 종류 추정 장치의 송수신기 전력 제어 방법 |
KR10-2022-0089331 | 2022-07-20 | ||
KR10-2022-0089328 | 2022-07-20 | ||
KR1020220089328A KR102615586B1 (ko) | 2022-07-20 | 2022-07-20 | 음파 신호를 이용한 노면 종류 추정 장치 및 그 방법 |
KR10-2022-0133405 | 2022-10-17 | ||
KR10-2022-0133387 | 2022-10-17 | ||
KR1020220133387A KR20240053377A (ko) | 2022-10-17 | 2022-10-17 | 비전센서와 음파센서가 구비된 도로 상태 모니터링 시스템 및 그 방법 |
KR1020220133405A KR20240053386A (ko) | 2022-10-17 | 2022-10-17 | 도로의 결빙 예방 장치의 제어 시스템 및 그 방법 |
KR1020220133397A KR20240053381A (ko) | 2022-10-17 | 2022-10-17 | 도로 인프라 센서 시공 구조물 및 이의 시공방법 |
KR10-2022-0133397 | 2022-10-17 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/439,766 Continuation US20240183117A1 (en) | 2021-11-17 | 2024-02-13 | Device and method for estimating and managing road surface types using sound signals |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023090758A1 true WO2023090758A1 (ko) | 2023-05-25 |
Family
ID=86397383
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2022/017680 WO2023090758A1 (ko) | 2021-11-17 | 2022-11-11 | 음파 신호를 이용하여 노면 종류를 추정하고 관리하는 장치 및 그 방법 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20240183117A1 (ko) |
EP (1) | EP4435706A1 (ko) |
CA (1) | CA3229412A1 (ko) |
WO (1) | WO2023090758A1 (ko) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117893045A (zh) * | 2024-01-16 | 2024-04-16 | 北京首发公路养护工程有限公司 | 基于深度学习实现道路养护下的融雪效果分析方法 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140059089A (ko) * | 2012-11-07 | 2014-05-15 | 현대모비스 주식회사 | 차량의 고속주행 적응형 초음파 센서 정보 처리 방법 |
KR20170069332A (ko) * | 2015-12-10 | 2017-06-21 | 현대모비스 주식회사 | 기상 환경에 따른 초음파 센서의 신호 보정 시스템 및 그 동작 방법 |
KR20180037468A (ko) * | 2016-10-04 | 2018-04-12 | 현대자동차주식회사 | 차량 데이터 기반의 노면 판단 방법 |
US20180265039A1 (en) * | 2017-03-16 | 2018-09-20 | Robert Bosch Gmbh | Intelligent Event System and Method for a Vehicle |
KR20200026146A (ko) * | 2018-08-29 | 2020-03-10 | 한국과학기술원 | 초음파 신호를 이용한 노면 종류 추정 방법 및 장치 |
KR102397312B1 (ko) * | 2021-11-17 | 2022-05-12 | 주식회사 모바휠 | 음파의 도메인 변환을 이용한 노면 종류 추정 장치 및 그 방법 |
KR102415195B1 (ko) * | 2021-11-17 | 2022-06-30 | 주식회사 모바휠 | 대기 감쇄량이 보정된 음파를 이용한 노면 종류 추정 장치 및 그 방법 |
-
2022
- 2022-11-11 EP EP22895965.6A patent/EP4435706A1/en active Pending
- 2022-11-11 CA CA3229412A patent/CA3229412A1/en active Pending
- 2022-11-11 WO PCT/KR2022/017680 patent/WO2023090758A1/ko active Application Filing
-
2024
- 2024-02-13 US US18/439,766 patent/US20240183117A1/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140059089A (ko) * | 2012-11-07 | 2014-05-15 | 현대모비스 주식회사 | 차량의 고속주행 적응형 초음파 센서 정보 처리 방법 |
KR20170069332A (ko) * | 2015-12-10 | 2017-06-21 | 현대모비스 주식회사 | 기상 환경에 따른 초음파 센서의 신호 보정 시스템 및 그 동작 방법 |
KR20180037468A (ko) * | 2016-10-04 | 2018-04-12 | 현대자동차주식회사 | 차량 데이터 기반의 노면 판단 방법 |
US20180265039A1 (en) * | 2017-03-16 | 2018-09-20 | Robert Bosch Gmbh | Intelligent Event System and Method for a Vehicle |
KR20200026146A (ko) * | 2018-08-29 | 2020-03-10 | 한국과학기술원 | 초음파 신호를 이용한 노면 종류 추정 방법 및 장치 |
KR102397312B1 (ko) * | 2021-11-17 | 2022-05-12 | 주식회사 모바휠 | 음파의 도메인 변환을 이용한 노면 종류 추정 장치 및 그 방법 |
KR102415195B1 (ko) * | 2021-11-17 | 2022-06-30 | 주식회사 모바휠 | 대기 감쇄량이 보정된 음파를 이용한 노면 종류 추정 장치 및 그 방법 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117893045A (zh) * | 2024-01-16 | 2024-04-16 | 北京首发公路养护工程有限公司 | 基于深度学习实现道路养护下的融雪效果分析方法 |
CN117893045B (zh) * | 2024-01-16 | 2024-07-05 | 北京首发公路养护工程有限公司 | 基于深度学习实现道路养护下的融雪效果分析方法 |
Also Published As
Publication number | Publication date |
---|---|
US20240183117A1 (en) | 2024-06-06 |
EP4435706A1 (en) | 2024-09-25 |
CA3229412A1 (en) | 2023-05-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2023090758A1 (ko) | 음파 신호를 이용하여 노면 종류를 추정하고 관리하는 장치 및 그 방법 | |
WO2020246631A1 (ko) | 온도 예측 모델의 생성 장치 및 시뮬레이션 환경의 제공 방법 | |
WO2020241922A1 (ko) | 차량 제어 장치 | |
WO2018038552A1 (ko) | 이동 로봇 및 그 제어방법 | |
WO2020213750A1 (ko) | 객체를 인식하는 인공 지능 장치 및 그 방법 | |
WO2018097574A1 (ko) | 이동 로봇 및 그 제어방법 | |
WO2018139796A1 (ko) | 이동 로봇 및 그의 제어 방법 | |
WO2020050499A1 (ko) | 객체 정보 획득 방법 및 이를 수행하는 장치 | |
WO2020196962A1 (ko) | 인공 지능 청소기 및 그의 동작 방법 | |
WO2017018729A1 (ko) | 차량용 레이더, 및 이를 구비하는 차량 | |
WO2018056515A1 (ko) | 차량용 카메라 장치 및 방법 | |
WO2019151845A2 (ko) | 에어컨 | |
EP3999286A1 (en) | Mobile robot and control method thereof | |
WO2020111880A1 (en) | User authentication method and apparatus | |
WO2021025217A1 (ko) | 인공지능 서버 | |
WO2020184747A1 (ko) | 오토 스탑 시스템을 제어하는 인공 지능 장치 및 그 방법 | |
WO2018124403A1 (ko) | 차량용 카메라 장치 및 차량 | |
WO2017018730A1 (ko) | 안테나, 차량용 레이더, 및 이를 구비하는 차량 | |
WO2018097424A1 (ko) | 차량용 통신 장치 및 차량 | |
WO2016028021A1 (ko) | 청소 로봇 및 그 제어 방법 | |
WO2018093192A1 (ko) | 차량용 레이더 장치 및 차량 | |
WO2019198942A1 (en) | Method of processing image, computer-readable storage medium recording method, and apparatus for processing image | |
WO2022164289A1 (ko) | 대상체의 기하학적 특성을 반영하여 확장된 표현 범위를 가지는 인텐시티 정보를 생성하는 방법 및 그러한 방법을 수행하는 라이다 장치 | |
WO2019168323A1 (ko) | 이상 개체 검출 장치 및 방법, 이를 포함하는 촬상 장치 | |
WO2022103236A1 (ko) | 선수 추적 방법, 선수 추적 장치 및 선수 추적 시스템 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22895965 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 3229412 Country of ref document: CA |
|
ENP | Entry into the national phase |
Ref document number: 2024529497 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280076362.1 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022895965 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2022895965 Country of ref document: EP Effective date: 20240617 |