CN111540212B - Highway interference estimation system and method for distributed optical fiber - Google Patents
Highway interference estimation system and method for distributed optical fiber Download PDFInfo
- Publication number
- CN111540212B CN111540212B CN202010652545.6A CN202010652545A CN111540212B CN 111540212 B CN111540212 B CN 111540212B CN 202010652545 A CN202010652545 A CN 202010652545A CN 111540212 B CN111540212 B CN 111540212B
- Authority
- CN
- China
- Prior art keywords
- information
- vehicle
- lane
- optical fiber
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000013307 optical fiber Substances 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims description 27
- 238000005303 weighing Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 54
- 238000013136 deep learning model Methods 0.000 claims description 32
- 238000013507 mapping Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000001133 acceleration Effects 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 15
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/02—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing wheeled or rolling bodies, e.g. vehicles
- G01G19/03—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing wheeled or rolling bodies, e.g. vehicles for weighing during motion
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P3/00—Measuring linear or angular speed; Measuring differences of linear or angular speeds
- G01P3/64—Devices characterised by the determination of the time taken to traverse a fixed distance
- G01P3/68—Devices characterised by the determination of the time taken to traverse a fixed distance using optical means, i.e. using infrared, visible, or ultraviolet light
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a highway interference estimation system for distributed optical fiber, comprising: the distributed optical fiber sensor is used for acquiring data information of the distributed optical fiber; the cameras are used for acquiring license plate information and road section information of the vehicle; the plurality of speed meters are used for acquiring the speed information of the vehicle; the weighing belt is used for acquiring weight information of the vehicle; the edge server is used for receiving license plate information and road section information sent by the cameras, vehicle speed information sent by the speedometers and weight information sent by the weighing belts, and sending the received license plate information, road section information, vehicle speed information and weight information to the cloud server through the Ethernet; and the cloud server is used for receiving and processing the data information sent by the distributed optical fiber sensor and the license plate information, the road section information, the vehicle speed information and the weight information sent by the edge server to obtain the interference condition of the vehicle on the distributed optical fiber.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a highway interference estimation system and method for distributed optical fibers.
Background
The distributed optical fiber sensing system can obtain the information of the spatial distribution state and the time variation of the measured parameters on the whole optical fiber length because any position of the optical fiber is a sensing unit. The distributed optical fiber sensing system can realize large-range monitoring, has a very important position in numerous optical fiber sensors, is the most mature technology and the most widely applied class, and shows good application prospect.
The highway automobile has large interference on the distributed optical fiber measurement vibration, so a complete interference estimation system is needed to effectively estimate highway automobile interference parameters such as amplitude, variance, covariance, frequency range and the like on the distributed optical fiber. The factors such as the flow, the weight and the speed of the automobile, the soil property around the highway and the like are various, and the time sequence data continuously changes along with the time, so that the interference of the highway automobile on the distributed optical fiber is not easy to estimate.
However, in the prior art, a highway interference estimation system for distributed optical fibers is not available. For example, patent publication No. CN101673463B discloses a traffic information prediction method and device based on time series, which relates to the field of communications. In order to quickly, efficiently and accurately predict traffic information, the technical scheme provided by the invention is as follows: acquiring a statistical value of road condition data of each time window of each road in each week characteristic day according to the stored historical road condition data; removing a trend item of reference road condition data of the predicted road according to the statistic value of the predicted road; acquiring a prediction equation of the predicted road according to the reference road condition data of the predicted road after the trend item is removed; and acquiring the predicted road condition data of the predicted road according to the prediction equation of the predicted road and the real-time road condition data of the predicted road. Although the method can predict traffic information, the method still cannot estimate the interference situation of the highway automobiles on the distributed optical fiber in real time.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a highway interference estimation system and method for a distributed optical fiber.
In order to achieve the purpose, the invention adopts the following technical scheme:
a highway interference estimation system for a distributed optical fiber, comprising: the system comprises a distributed optical fiber sensor, a plurality of cameras, a plurality of velocimeters, a weighing belt, an edge server, an Ethernet and a cloud server; the distributed optical fiber sensor is arranged underground of the highway, the edge server, the cameras and the velocimeters are respectively arranged on the highway, and the weighing belt is arranged at the entrance of the highway;
the distributed optical fiber sensor is used for acquiring data information of a distributed optical fiber and sending the acquired data information to the cloud server through the Ethernet;
the cameras are used for acquiring license plate information and road section information of a vehicle and sending the license plate information and the road section information of the vehicle to the edge server;
the plurality of speed meters are used for acquiring the speed information of the vehicle and sending the speed information of the vehicle to the edge server;
the weighing belt is used for acquiring weight information of the vehicle and sending the weight information of the vehicle to the edge server;
the edge server is used for receiving license plate information and road section information sent by the cameras, vehicle speed information sent by the velocimeters and weight information sent by the weighing belts, and sending the received license plate information, road section information, vehicle speed information and weight information to the cloud server through the Ethernet;
and the cloud server is used for receiving and processing data information sent by the distributed optical fiber sensor and license plate information, road section information, vehicle speed information and weight information sent by the edge server to obtain the interference condition of the vehicle on the distributed optical fiber.
Furthermore, the road section information is a road section within a preset range of the distributed optical fiber, the road section is averagely divided into a plurality of lane sections, and a camera and a velocimeter are arranged on one side of each lane section.
Further, the edge server specifically includes:
the first judgment module is used for judging whether the received license plate information of the current vehicle exists in the link hash mapping;
the storage module is used for storing the license plate information, the lane section information, the vehicle speed information and the weight information of the current vehicle in the link hash mapping when the license plate information of the current vehicle does not exist in the link hash mapping;
the second judgment module is used for judging whether the current vehicle is in the next lane section or not;
the updating module is used for updating the lane section information and the vehicle speed information of the current vehicle in the link hash mapping when the current vehicle is in the next lane section;
the third judgment module is used for judging whether the current vehicle leaves the whole road section;
and the deleting module is used for deleting the license plate information, the lane section information, the vehicle speed information and the weight information of the current vehicle when the current vehicle leaves the whole road section.
Further, the edge server is further configured to fit lane segment information of the vehicle, and specifically includes:
the first calculation module is used for calculating the acceleration of the current vehicle in the current lane section;
wherein,
representing a speed at which the current vehicle enters the current lane segment;
representing a speed at which the current vehicle leaves the current lane segment;
representing the total stay time of the current vehicle in the current lane section;
the second calculation module is used for calculating the speed of the current vehicle at any time point according to the acceleration of the current vehicle in the current lane section;
wherein,
representing a dwell time of the current vehicle within the current lane segment;
the estimation module is used for estimating the lane change times of the current vehicle in the lane section according to the position of the current vehicle entering and exiting the current lane section and estimating the lane section at any time point according to the lane change times;
an extraction module for extracting the weight of the current vehicleW；
Input module for transmitting all vehicles at any timeSpeed of the vehicleVWeight of vehicleWAnd inputting the vehicle parameters into the parameter matrix to obtain the parameter matrix of the vehicle.
Further, the cloud server is further used for establishing a deep learning model based on a deep learning network, and obtaining the interference condition of the vehicle on the distributed optical fiber according to the established deep learning model.
Correspondingly, the method for estimating the highway interference for the distributed optical fiber comprises the following steps:
s1, a distributed optical fiber sensor acquires data information of a distributed optical fiber and sends the acquired data information to a cloud server through an Ethernet;
s2, a plurality of cameras acquire license plate information and road section information of a vehicle and send the license plate information and the road section information of the vehicle to an edge server;
s3, obtaining the speed information of the vehicle by a plurality of speed meters, and sending the speed information of the vehicle to an edge server;
s4, the weighing belt acquires weight information of the vehicle and sends the weight information of the vehicle to an edge server;
s5, the edge server receives license plate information and road section information sent by a plurality of cameras, vehicle speed information sent by a plurality of speed meters and weight information sent by the weighing belt, and sends the received license plate information, road section information, vehicle speed information and weight information to the cloud server through the Ethernet;
and S6, the cloud server receives and processes data information sent by the distributed optical fiber sensor and license plate information, road section information, vehicle speed information and weight information sent by the edge server to obtain the interference condition of the vehicle on the distributed optical fiber.
Furthermore, the road section information is a road section within a preset range of the distributed optical fiber, the road section is averagely divided into a plurality of lane sections, and a camera and a velocimeter are arranged on one side of each lane section.
Further, the step S5 includes:
A1. judging whether the received license plate information of the current vehicle exists in the link hash mapping, if so, executing the step A3; if not, executing the step A2;
A2. storing license plate information, lane section information, vehicle speed information and weight information of the current vehicle in a linked hash map;
A3. judging whether the current vehicle is in the next lane section, if so, executing the step A4; if not, executing the step A5;
A4. updating lane section information and vehicle speed information of the current vehicle in the link hash mapping;
A5. judging whether the current vehicle leaves the whole road section, if so, executing the step A6; if not, executing the step A3;
A6. and deleting the license plate information, the lane section information, the vehicle speed information and the weight information of the current vehicle.
Further, the step S5 further includes fitting lane segment information of the vehicle, specifically:
B1. calculating the acceleration of the current vehicle in the current lane section;
wherein,
representing a speed at which the current vehicle enters the current lane segment;
representing a speed at which the current vehicle leaves the current lane segment;
representing the total stay time of the current vehicle in the current lane section;
B2. calculating the speed of the current vehicle at any time point according to the acceleration of the current vehicle in the current lane section;
wherein,
representing a dwell time of the current vehicle within the current lane segment;
B3. the lane change times of the current vehicle in the lane section are estimated according to the position of the current vehicle entering and exiting the current lane section, and the lane section where any time point is located is estimated according to the lane change times;
B4. extracting the weight of the current vehicleW；
B5. The speed of all vehicles at any time pointVWeight of vehicleWAnd inputting the vehicle parameters into the parameter matrix to obtain the parameter matrix of the vehicle.
Further, the step S6 further includes establishing a deep learning model based on a deep learning network, and obtaining an interference situation caused by the vehicle to the distributed optical fiber according to the established deep learning model.
Compared with the prior art, the method can estimate the interference condition of the highway automobile to the distributed optical fiber in real time, and further provides a basis for eliminating the interference in the later period. For example, distributed optical fibers are deployed in gas pipelines for monitoring whether the gas pipelines may be damaged by the outside, such as excavators, pile drivers, and the like. If the current automobile driving condition of the highway is not enough to cause the current distributed optical fiber data condition, the excavator, the pile driver and the like are likely to enter the optical fiber deployment area, and an alarm is needed.
Drawings
FIG. 1 is a schematic cross-sectional view of a distributed optical fiber and a highway provided by one embodiment;
fig. 2 is an architecture diagram of an interference estimation system according to an embodiment;
FIG. 3 is a schematic diagram of an embodiment providing a highway right-hand lane sensor deployment;
FIG. 4 is a schematic diagram of a highway right-direction lane parameter matrix provided in the first embodiment;
FIG. 5 is a hash mapping table of vehicle driving information provided in accordance with one embodiment;
fig. 6 is a schematic diagram of a deep learning model for interference estimation according to an embodiment.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
The invention aims to provide a distributed optical fiber highway interference estimation system and method aiming at the defects of the prior art.
Example one
The present embodiment provides a highway interference estimation system for a distributed optical fiber, as shown in fig. 1-2, including: the system comprises a distributed optical fiber sensor 11, a plurality of cameras 12, a plurality of velocimeters 13, a weighing belt 14, an edge server 15, an Ethernet 17 and a cloud server 16; the distributed optical fiber sensor is arranged underground of the highway, the edge server, the cameras and the velocimeters are respectively arranged on the highway, and the weighing belt is arranged at the entrance of the highway;
the distributed optical fiber sensor 11 is used for acquiring data information of the distributed optical fiber and sending the acquired data information to the cloud server through the Ethernet;
the cameras 12 are used for acquiring license plate information and road section information of the vehicle and sending the license plate information and the road section information of the vehicle to the edge server;
the plurality of speed meters 13 are used for acquiring the speed information of the vehicle and sending the speed information of the vehicle to the edge server;
the weighing belt 14 is used for acquiring weight information of the vehicle and sending the weight information of the vehicle to the edge server;
the edge server 15 is used for receiving license plate information and road section information sent by the cameras, vehicle speed information sent by the velocimeters and weight information sent by the weighing belts, and sending the received license plate information, road section information, vehicle speed information and weight information to the cloud server through the Ethernet;
and the cloud server 16 is used for receiving and processing the data information sent by the distributed optical fiber sensor and the license plate information, the road section information, the vehicle speed information and the weight information sent by the edge server to obtain the interference condition of the vehicle on the distributed optical fiber.
In the distributed optical fiber sensor 11, data information of the distributed optical fiber is acquired, and the acquired data information is sent to the cloud server through the ethernet.
Fig. 1 is a schematic cross-sectional view of a distribution optical fiber and a highway. The distributed optical fibers are deployed underground along with the gas pipeline and are arranged in a crossed manner with the highway on the ground. The motorway cars have a large influence on the measurement results of the distributed optical fiber. The highway takes four bidirectional lanes as an example, four lanes in the right direction and four lanes in the left direction, and the middle of the highway is divided by a green belt.
Fig. 2 shows an architecture diagram of an interference estimation system. The distributed optical fiber and highway data acquisition system mainly comprises a distributed optical fiber sensor, a camera matrix, a velometer matrix, a weighing belt, an edge server, an Ethernet and a cloud server; the distributed optical fiber sensor can send data to the cloud server in real time through the Ethernet; the edge server is deployed at the side of the expressway, the driving condition (namely a parameter matrix) of the automobile segmented (namely a lane segment) through the expressway is obtained through calculation of the camera matrix, the velometer matrix and the weighing belt, and the driving condition is sent to the cloud server; the cloud server is responsible for data integration, interference estimation and storage.
In this embodiment, the highway selects a section of road closer to the distributed optical fiber sensor (that is, within a preset range of the distributed optical fiber sensor, all the distributed optical fiber sensors can be covered), and equally divides the selected section into a plurality of sub-sections, that is, a plurality of lane sections, and a camera and a velometer are installed at the entrance and exit of each lane section, thereby forming a camera matrix and a velometer matrix. Fig. 3 shows a schematic diagram of the sensor deployment of the right-hand lane of the highway, and a vehicle enters the section of the highway from the left side of the lane. The weighing belt and the camera are matched to acquire the weight of the automobile marked by the license plate, so that the weight of the automobile in the highway subsection can be acquired. The camera and the velometer are matched to obtain the automobile speed condition in the highway subsection. And the lane between two adjacent groups of cameras and velocimeters is called a lane section. For example, the selected highway is 200 meters in total, a group of cameras and velocimeters are deployed every 50 meters, and each lane is divided into 4 lane segments. In addition, 5 groups of cameras and 5 groups of velocimeters need to be configured.
The distributed optical fiber sensor mainly comprises: the device comprises an ultra-narrow line width laser, an acoustic optical modulator, a circulator, a photoelectric detector, a sensing optical fiber, a pre-amplification circuit, a data acquisition card, a host and the like. In practical engineering applications, an ultra-narrow linewidth laser, an acousto-optic modulator, a circulator, a photoelectric detector and other corresponding power supply, driving and detection circuits and a communication interface are generally integrated in a sensor host; the sensing optical fiber is arranged in a sensing optical cable of an external field. The laser emitted by the ultra-narrow line width laser as a light source is modulated into light pulses by the acousto-optic modulator, the light pulses are injected into the sensing optical fiber through the circulator, backward Rayleigh scattering light in the sensing optical fiber generates coherent interference within the pulse width, the interference light intensity is detected by the detector through the circulator, and the interference light intensity is amplified and enters the host machine through the data acquisition card to perform data processing and result display.
When disturbance action is applied to the sensing optical fiber, due to the elasto-optical effect, the optical phase of a disturbed position changes, so that the phase of backward scattering light at a corresponding position changes, and the interference light intensity of the scattering light in the pulse width also changes correspondingly, so that the distributed optical fiber sensor acquires corresponding data information of the distributed optical fiber.
The cameras 12 are used for acquiring license plate information and road section information of the vehicle and sending the license plate information and the road section information of the vehicle to the edge server.
Each camera in the plurality of cameras is arranged at an inlet and an outlet of each lane section of the road section and is used for shooting automobile license plate information, road section information, the time when the automobile is in the lane section and the like.
And the plurality of speed meters 13 are used for acquiring the speed information of the vehicle and sending the speed information of the vehicle to the edge server.
Each of the plurality of speedometers is arranged at an inlet and an outlet of each lane section of the road section and used for measuring the speed of the automobile.
The system combines the parameters of the lane sections to form a parameter matrix (see the specific parameter matrix and the relationship of the lane sections in figures 3 and 4)
And the weighing belt 14 is used for acquiring the weight information of the vehicle and sending the weight information of the vehicle to the edge server.
Because the weight of the automobile in the highway is not changed, a weighing belt is mainly required to be installed at the entrance of the complete highway, when the automobile reaches the entrance of the highway, the weighing belt arranged at the entrance measures the weight of the automobile, and the weighing belt does not need to be measured again in the subsequent driving process.
In the edge server 15, the license plate information and the road segment information sent by the plurality of cameras, the vehicle speed information sent by the plurality of speed meters, and the weight information sent by the weighing belt are received, and the received license plate information, road segment information, vehicle speed information, and weight information are sent to the cloud server through the ethernet.
After the road section is divided into a plurality of lane sections, a parameter matrix is formed by combining lanes (such as a passing lane, a traffic lane, an emergency lane and the like) of the highway per se, and the highway comprises a plurality of lanes according to actual conditions, as shown in fig. 3, the highway per se of the embodiment has 4 lanes, and the road section selected in the preset range of the distributed optical fiber is divided into 4 lane sections, so that a parameter matrix schematic diagram of the right-direction lane of the highway shown in fig. 4 is obtained, and specifically, the automobile driving condition of the right-direction lane of the highway is divided into 4 sections, and the 4 lanes are 16 sections. The vehicle operating parameters Pnn (such as P11) include 2 parameters-vehicle weight and vehicle speed. Calculating a left lane, wherein the lane section reaches 32 sections, and the parameter matrix has 64 parameters.
The driving conditions of the automobile comprise the weight, the speed, the lane section and the like of the automobile. The automobile can be weighed by the weighing belt before entering the highway; the speed measuring instrument can measure the speed each time the automobile drives each lane section; the camera captures the license plate and the lane section of the automobile, and then information such as the license plate, the weight of the automobile, the speed of the automobile, the lane section where the automobile is located and the like is stored in a pre-established link hash map. The method specifically comprises the following steps:
the first judgment module is used for judging whether the received license plate information of the current vehicle exists in the link hash mapping;
after the automobile enters the selected road section, the edge server judges whether the license plate information of the current automobile is stored in the link hash mapping or not, if not, the information related to the automobile corresponding to the license plate is stored; and if so, performing the next judgment. If the current vehicle enters the lane segment P41, it is first determined whether the license plate is stored in the link hash map, and if not, the vehicle-related information is stored.
The hash mapping is linked, the hash map is used for storing data, and the value corresponding to the key can be quickly found. And, the link hash map is linked by a linked list according to the order of data insertion.
The storage module is used for storing the license plate information, the lane section information, the vehicle speed information and the weight information of the current vehicle in the link hash mapping when the license plate information of the current vehicle does not exist in the link hash mapping;
and when the judgment result shows that the link hash mapping does not have the license plate information of the current vehicle, the edge server acquires the relevant information of the current vehicle from a camera, a velometer and a weighing belt arranged at the entrance of the expressway, wherein the camera, the velometer and the weighing belt are arranged beside the road. In the linked hash map, the key is the license plate number and the values include the weight of the car, the current lane segment, the timestamp of the incoming lane segment, and the speed, as shown in FIG. 5.
The second judgment module is used for judging whether the current vehicle is in the next lane section or not;
in the embodiment, whether the current vehicle enters the next lane segment is judged, and if yes, the information of the vehicle in the link hash mapping is updated; if not, the next judgment is carried out. The embodiment judges the information of the lane section where the vehicle is located, and aims to know the driving state of the vehicle in time.
The updating module is used for updating the lane section information and the vehicle speed information of the current vehicle in the link hash mapping when the current vehicle is in the next lane section;
and after the vehicle enters the next lane section, updating the timestamp and the speed of the current lane section where the vehicle is located and the lane entering section in the link hash mapping, wherein the weight information of the vehicle does not need to be updated because the weight of the vehicle is unchanged.
The third judgment module is used for judging whether the current vehicle leaves the whole road section;
in this embodiment, it is determined whether the current vehicle leaves the entire lane segment (i.e., the selected lane segment), and if so, the information of the vehicle in the link hash map is deleted; if not, whether the vehicle enters the next lane section is continuously judged.
And the deleting module is used for deleting the license plate information, the lane section information, the vehicle speed information and the weight information of the current vehicle when the current vehicle leaves the whole road section.
When the vehicle leaves the selected road section, the information (license plate, automobile weight, current lane section, time stamp and speed of entering lane section) of the vehicle in the link hash mapping is deleted, so that the data of the village number in the link hash mapping is reduced, and the data memory in the edge server is reduced.
In this embodiment, the edge side server packs the driving information of the car at regular time intervals. Because the time and the speed of the automobile entering the lane are different, the sampling period of the automobile driving information is not fixed, or because blind zones exist and the information obtained by a camera and a velocimeter is inaccurate due to the fact that each lane section is too long, the estimation needs to be carried out through a certain fitting algorithm, the automobile driving information is further calculated, and then a parameter matrix of a certain time point is obtained. The specific calculation comprises the following steps:
the first calculation module is used for calculating the acceleration of the current vehicle in the current lane section;
the velocimeter obtains the speed of the automobile entering a certain lane section
Speed of exiting a certain lane section
The camera records the time when the automobile enters a certain lane section and the time when the automobile leaves the certain lane section, then the time when the automobile is in the certain lane section is calculated as Δ T according to the entering time and the leaving time, and the vehicle speed is obtained according to the obtained value
、
And the obtained time Δ T is used for further calculating the acceleration in the lane section (wherein the acceleration only needs to be calculated once).
Wherein,
representing a speed at which the current vehicle enters the current lane segment;
representing a speed at which the current vehicle leaves the current lane segment;
representing the total stay time of the current vehicle in the current lane section;
the second calculation module is used for calculating the speed of the current vehicle at any time point according to the acceleration of the current vehicle in the current lane section;
based on calculated vehicles in a certain lane sectionThe acceleration can be calculated to obtain the speed at any time point, for example, the speed of the vehicle at a time point T can be obtained when the vehicle enters a lane segment
；
Wherein,
representing a dwell time of the current vehicle within the current lane segment;
the estimation module is used for estimating the lane change times of the current vehicle in the lane section according to the position of the current vehicle entering and exiting the current lane section and estimating the lane section at any time point according to the lane change times;
in the embodiment, the possibility of lane change of the automobile during running on the expressway is considered, a lane where the automobile enters a certain lane section is set as a lane different from a parking space where the automobile leaves the lane section, and lane change times N, namely the number of lane intervals, can be deduced by entering and exiting the lane section; for example, if the automobile is in the lane section (P11, P21, P31, P41), the lane entering the lane section is P21, and the lane leaving the lane section is P41, so that it can be estimated that the number of lane changes of the automobile from entering the lane section to leaving the lane section is 3 times in total.
Then the time of the automobile in the lane section calculated in the first calculation module is obtained
The vehicle is divided into N sections on average, and the lane section where the vehicle is located at any time point can be estimated.
An extraction module for extracting the weight of the current vehicleW；
Since the weight W of the car does not change, the weight does not need to be re-estimated and is directly taken through the side weight belt.
An input module for connectingSpeed of all vehicles at an arbitrary time pointVWeight of vehicleWAnd inputting the vehicle parameters into the parameter matrix to obtain the parameter matrix of the vehicle.
According to the calculation method, the information of all vehicles in the selected road section at any time, namely the speed V and the weight W, is obtained, and the speed V and the weight W are filled in the parameter matrix. Wherein each parameter of the parameter matrix corresponds to a lane segment. In this embodiment, if the distance between the cars exceeds 50 meters, the length of each lane segment is 50 meters, and a plurality of cars do not appear in one lane segment.
However, if the length of each lane segment is long in order to save equipment resources, a plurality of vehicles in the same lane segment can be obtained, and the weight and the speed of the vehicle in the lane segment can be calculated according to the following formula.
In the cloud server 16, the data information sent by the distributed optical fiber sensor and the license plate information, the road section information, the vehicle speed information and the weight information sent by the edge server are received and processed, so that the interference condition of the vehicle on the distributed optical fiber is obtained.
The cloud server is further used for establishing a deep learning model based on the deep learning network, and obtaining the interference condition of the vehicle to the distributed optical fibers according to the established deep learning model.
In the embodiment, the lane section is taken as a unit, the parameter matrix (including the weight and the speed of the automobile) is transmitted to the cloud server, then a deep learning model is established based on the parameter matrix and the data information of the distributed optical fiber and on the basis of deep learning network training, and the relationship between the driving condition of the automobile on the highway and the interference condition of the distributed optical fiber is estimated. The method specifically comprises the following steps:
the deep learning model needs to estimate the variance, covariance, amplitude and frequency range of some points of the distributed optical fiber in a period of time, and inputs the variance, covariance, amplitude and frequency range as a parameter matrix time sequence of the expressway. The method comprises the following specific steps:
firstly, calculating and selecting data to obtain time sequence data statistic of a certain point of the distributed optical fiber and a corresponding parameter matrix time sequence,
(1) calculating time series data statistics of a certain point of the distributed optical fiber in time [ T1, T2] (the time window size is T2-T1), for example, selecting a point 200 meters away from a laser emission point, and calculating variance, covariance, amplitude, frequency range and the like;
(2) selecting a parameter matrix time sequence within time [ T0, T2] (T0 is earlier than T1, a time window is slightly larger than T2-T1) as the input of a deep learning model, wherein the time intervals of adjacent parameter matrices in the parameter matrix time sequence are the same, and the specific parameter matrix is obtained by a calculation mode in an edge server;
then, model training is performed using the parameter matrix time-series data.
And taking the time sequence data of the parameter matrix as input, taking the distributed optical fiber statistics such as variance, covariance, amplitude, frequency range and the like as output, and training a deep learning model. The deep learning model firstly carries out convolution calculation on the parameter matrix time sequence for multiple times, and then carries out Conv-LSTM calculation on the convolution result of each time to obtain a plurality of parameter matrices with different dimensions. And splicing a plurality of parameter matrixes with different dimensions into one parameter matrix, and outputting the parameter matrix through a neural network. The loss function is combined with the variance, covariance, amplitude, frequency range and the like to obtain an actual measurement result and a mean square error output by the model. And further, the parameters of the deep learning model are obtained through the back propagation algorithm optimization. The concrete model is shown in figure 6.
It should be noted that, the scheme of how to train the deep learning network model is similar to the training mode in the prior art, and this embodiment is not described herein again.
(3) Interference estimation
The method comprises the steps of obtaining a parameter matrix of a certain time interval in real time according to a calculation mode in an edge server, selecting the parameter matrix corresponding to the size of a time window every time, inputting the parameter matrix into an interference estimation deep learning model of a certain point of the distributed optical fiber to be estimated, outputting time sequence data statistics of the point of the distributed optical fiber to be estimated by the model, wherein the statistics comprises variance, covariance, amplitude and frequency range, and finally estimating the interference condition of a highway automobile on the distributed optical fiber to provide a basis for later interference elimination.
Fig. 6 shows an example of a deep learning model for interference estimation, where the convolution and the number of Conv-LSTM layers can be adjusted according to the situation. The deep learning model is input as a parameter model time sequence, and a parameter matrix of 4 continuous time points is input in the graph. The dimension of the parameter matrix is 4 × 8 × 2, 4 represents the number of lane segments of a single lane, 8 represents the number of lanes in a bidirectional lane, and 2 represents two parameters, namely the weight and the speed of the vehicle. The deep learning model firstly carries out convolution calculation on the parameter matrix time sequence for multiple times, and then carries out Conv-LSTM calculation on the convolution result of each time to obtain a plurality of parameter matrices with different dimensions. And splicing a plurality of parameter matrixes with different dimensions into one parameter matrix, and outputting the parameter matrix through a neural network module NN. The loss function is combined with the variance, covariance, amplitude, frequency range and the like to obtain an actual measurement result and a mean square error output by the model. And further, the parameters of the deep learning model are obtained through the back propagation algorithm optimization.
The highway interference estimation system for the distributed optical fiber can estimate the interference condition of a highway automobile on the distributed optical fiber in real time, and further provides a basis for eliminating interference in the later period.
Example two
The embodiment provides a highway interference estimation method for a distributed optical fiber, which comprises the following steps:
s11, a distributed optical fiber sensor acquires data information of a distributed optical fiber and sends the acquired data information to a cloud server through an Ethernet;
s12, acquiring license plate information and road section information of a vehicle by a plurality of cameras, and sending the license plate information and the road section information of the vehicle to an edge server;
s13, obtaining the speed information of the vehicle by a plurality of speed meters, and sending the speed information of the vehicle to an edge server;
s14, the weighing belt acquires weight information of the vehicle and sends the weight information of the vehicle to an edge server;
s15, the edge server receives license plate information and road section information sent by a plurality of cameras, vehicle speed information sent by a plurality of speed meters and weight information sent by the weighing belt, and sends the received license plate information, road section information, vehicle speed information and weight information to the cloud server through the Ethernet;
and S16, the cloud server receives and processes data information sent by the distributed optical fiber sensor and license plate information, road section information, vehicle speed information and weight information sent by the edge server to obtain the interference condition of the vehicle on the distributed optical fiber.
Furthermore, the road section information is a road section within a preset range of the distributed optical fiber, the road section is averagely divided into a plurality of lane sections, and a camera and a velocimeter are arranged on one side of each lane section.
Further, the step S15 includes:
A1. judging whether the received license plate information of the current vehicle exists in the link hash mapping, if so, executing the step A3; if not, executing the step A2;
A2. storing license plate information, lane section information, vehicle speed information and weight information of the current vehicle in a linked hash map;
A3. judging whether the current vehicle is in the next lane section, if so, executing the step A4; if not, executing the step A5;
A4. updating lane section information and vehicle speed information of the current vehicle in the link hash mapping;
A5. judging whether the current vehicle leaves the whole road section, if so, executing the step A6; if not, executing the step A3;
A6. and deleting the license plate information, the lane section information, the vehicle speed information and the weight information of the current vehicle.
Further, the step S15 further includes fitting lane segment information of the vehicle, specifically:
B1. calculating the acceleration of the current vehicle in the current lane section;
wherein,
representing a speed at which the current vehicle enters the current lane segment;
representing a speed at which the current vehicle leaves the current lane segment;
representing the total stay time of the current vehicle in the current lane section;
B2. calculating the speed of the current vehicle at any time point according to the acceleration of the current vehicle in the current lane section;
wherein,
representing a dwell time of the current vehicle within the current lane segment;
B3. the lane change times of the current vehicle in the lane section are estimated according to the position of the current vehicle entering and exiting the current lane section, and the lane section where any time point is located is estimated according to the lane change times;
B4. extracting the weight of the current vehicleW；
B5. The speed of all vehicles at any time pointVWeight of vehicleWAnd inputting the vehicle parameters into the parameter matrix to obtain the parameter matrix of the vehicle.
Further, the step S16 further includes establishing a deep learning model based on a deep learning network, and obtaining an interference situation caused by the vehicle to the distributed optical fiber according to the established deep learning model.
It should be noted that, the method for estimating the highway interference for the distributed optical fiber provided in this embodiment is similar to the embodiment, and is not repeated herein.
Compared with the prior art, the method and the device can estimate the interference condition of the highway automobile to the distributed optical fiber in real time, and further provide a basis for eliminating the interference in the later period. For example, distributed optical fibers are deployed in gas pipelines for monitoring whether the gas pipelines may be damaged by the outside, such as excavators, pile drivers, and the like. If the current automobile driving condition of the highway is not enough to cause the current distributed optical fiber data condition, the excavator, the pile driver and the like are likely to enter the optical fiber deployment area, and an alarm is needed.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (8)
1. A system for estimating highway interference of a distributed optical fiber, comprising: the system comprises a distributed optical fiber sensor, a plurality of cameras, a plurality of velocimeters, a weighing belt, an edge server, an Ethernet and a cloud server; the distributed optical fiber sensor is arranged underground of the highway, the edge server, the cameras and the velocimeters are respectively arranged on the highway, and the weighing belt is arranged at the entrance of the highway;
the distributed optical fiber sensor is used for acquiring data information of a distributed optical fiber and sending the acquired data information to the cloud server through the Ethernet;
the cameras are used for acquiring license plate information and road section information of a vehicle and sending the license plate information and the road section information of the vehicle to the edge server;
the plurality of speed meters are used for acquiring the speed information of the vehicle and sending the speed information of the vehicle to the edge server;
the weighing belt is used for acquiring weight information of the vehicle and sending the weight information of the vehicle to the edge server;
the edge server is used for receiving license plate information and road section information sent by the cameras, vehicle speed information sent by the velocimeters and weight information sent by the weighing belts, and sending the received license plate information, road section information, vehicle speed information and weight information to the cloud server through the Ethernet;
the cloud server is used for receiving and processing data information sent by the distributed optical fiber sensor and license plate information, road section information, vehicle speed information and weight information sent by the edge server to obtain the interference condition of the vehicle on the distributed optical fiber;
the cloud server is further used for establishing a deep learning model based on a deep learning network, and obtaining the interference condition of the vehicle on the distributed optical fiber according to the established deep learning model;
the method specifically comprises the following steps:
(1) calculating time series data statistics of a certain point of the distributed optical fiber within time [ T1, T2 ];
(2) selecting a parameter matrix time sequence within time [ T0, T2] as the input of a deep learning model and carrying out model training to obtain the deep learning model; wherein T0 is earlier than T1, and the time intervals of the adjacent parameter matrixes in the parameter matrix time sequence are the same;
(3) and inputting the parameter matrix of the time interval into a deep learning model, outputting the estimated time sequence data statistics of the distributed optical fiber point by the deep learning model, including variance, covariance, amplitude and frequency range, and estimating the interference condition of the expressway automobile on the distributed optical fiber.
2. The system of claim 1, wherein the section information is a section within a preset range of the distributed optical fiber, the section is divided into a plurality of lane segments on average, and a camera and a velocimeter are disposed on one side of each lane segment.
3. The system of claim 2, wherein the edge server comprises:
the first judgment module is used for judging whether the received license plate information of the current vehicle exists in the link hash mapping;
the storage module is used for storing the license plate information, the lane section information, the vehicle speed information and the weight information of the current vehicle in the link hash mapping when the license plate information of the current vehicle does not exist in the link hash mapping;
the second judgment module is used for judging whether the current vehicle is in the next lane section or not;
the updating module is used for updating the lane section information and the vehicle speed information of the current vehicle in the link hash mapping when the current vehicle is in the next lane section;
the third judgment module is used for judging whether the current vehicle leaves the whole road section;
and the deleting module is used for deleting the license plate information, the lane section information, the vehicle speed information and the weight information of the current vehicle when the current vehicle leaves the whole road section.
4. The system according to claim 3, wherein the edge server is further configured to fit lane segment information of a vehicle, and specifically comprises:
the first calculation module is used for calculating the acceleration of the current vehicle in the current lane section;
wherein,
representing a speed at which the current vehicle enters the current lane segment;
representing a speed at which the current vehicle leaves the current lane segment;
representing the total stay time of the current vehicle in the current lane section;
the second calculation module is used for calculating the speed of the current vehicle at any time point according to the acceleration of the current vehicle in the current lane section;
wherein,
representing a dwell time of the current vehicle within the current lane segment;
the estimation module is used for estimating the lane change times of the current vehicle in the lane section according to the position of the current vehicle entering and exiting the current lane section and estimating the lane section at any time point according to the lane change times;
an extraction module for extracting the weight of the current vehicleW；
An input module for converting the speed of all vehicles at any time pointVWeight of vehicleWAnd inputting the vehicle parameters into the parameter matrix to obtain the parameter matrix of the vehicle.
5. A method for estimating highway interference of a distributed optical fiber is characterized by comprising the following steps:
s1, a distributed optical fiber sensor acquires data information of a distributed optical fiber and sends the acquired data information to a cloud server through an Ethernet;
s2, a plurality of cameras acquire license plate information and road section information of a vehicle and send the license plate information and the road section information of the vehicle to an edge server;
s3, obtaining the speed information of the vehicle by a plurality of speed meters, and sending the speed information of the vehicle to an edge server;
s4, the weighing belt acquires weight information of the vehicle and sends the weight information of the vehicle to an edge server;
s5, the edge server receives license plate information and road section information sent by a plurality of cameras, vehicle speed information sent by a plurality of speed meters and weight information sent by the weighing belt, and sends the received license plate information, road section information, vehicle speed information and weight information to the cloud server through the Ethernet;
s6, the cloud server receives and processes data information sent by the distributed optical fiber sensor and license plate information, road section information, vehicle speed information and weight information sent by the edge server to obtain the interference condition of the vehicle on the distributed optical fiber;
the step S6 further includes establishing a deep learning model based on a deep learning network, and obtaining the interference condition of the vehicle to the distributed optical fiber according to the established deep learning model;
the method specifically comprises the following steps:
(1) calculating time series data statistics of a certain point of the distributed optical fiber within time [ T1, T2 ];
(2) selecting a parameter matrix time sequence within time [ T0, T2] as the input of a deep learning model and carrying out model training to obtain the deep learning model; wherein T0 is earlier than T1, and the time intervals of the adjacent parameter matrixes in the parameter matrix time sequence are the same;
(3) and inputting the parameter matrix of the time interval into a deep learning model, outputting the estimated time sequence data statistics of the distributed optical fiber point by the deep learning model, including variance, covariance, amplitude and frequency range, and estimating the interference condition of the expressway automobile on the distributed optical fiber.
6. The method as claimed in claim 5, wherein the road section information is a road section within a preset range of the distributed optical fiber, the road section is divided into a plurality of lane sections on average, and a camera and a velocimeter are disposed on one side of each lane section.
7. The method for estimating highway interference according to claim 6, wherein said step S5 comprises:
A1. judging whether the received license plate information of the current vehicle exists in the link hash mapping, if so, executing the step A3; if not, executing the step A2;
A2. storing license plate information, lane section information, vehicle speed information and weight information of the current vehicle in a linked hash map;
A3. judging whether the current vehicle is in the next lane section, if so, executing the step A4; if not, executing the step A5;
A4. updating lane section information and vehicle speed information of the current vehicle in the link hash mapping;
A5. judging whether the current vehicle leaves the whole road section, if so, executing the step A6; if not, executing the step A3;
A6. and deleting the license plate information, the lane section information, the vehicle speed information and the weight information of the current vehicle.
8. The method according to claim 7, wherein the step S5 further includes fitting lane segment information of the vehicle, specifically:
B1. calculating the acceleration of the current vehicle in the current lane section;
wherein,
indicating that the current vehicle is entering the currentSpeed of the lane segment;
representing a speed at which the current vehicle leaves the current lane segment;
representing the total stay time of the current vehicle in the current lane section;
B2. calculating the speed of the current vehicle at any time point according to the acceleration of the current vehicle in the current lane section;
wherein,
representing a dwell time of the current vehicle within the current lane segment;
B3. the lane change times of the current vehicle in the lane section are estimated according to the position of the current vehicle entering and exiting the current lane section, and the lane section where any time point is located is estimated according to the lane change times;
B4. extracting the weight of the current vehicleW；
B5. The speed of all vehicles at any time pointVWeight of vehicleWAnd inputting the vehicle parameters into the parameter matrix to obtain the parameter matrix of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010652545.6A CN111540212B (en) | 2020-07-08 | 2020-07-08 | Highway interference estimation system and method for distributed optical fiber |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010652545.6A CN111540212B (en) | 2020-07-08 | 2020-07-08 | Highway interference estimation system and method for distributed optical fiber |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111540212A CN111540212A (en) | 2020-08-14 |
| CN111540212B true CN111540212B (en) | 2020-09-25 |
Family
ID=71979723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010652545.6A Active CN111540212B (en) | 2020-07-08 | 2020-07-08 | Highway interference estimation system and method for distributed optical fiber |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111540212B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538895B (en) * | 2020-10-15 | 2024-02-09 | 腾讯科技（深圳）有限公司 | Vehicle regulation and control method, device and system and computer storage medium |
| CN115410403B (en) * | 2022-04-19 | 2023-11-10 | 北京见合八方科技发展有限公司 | Road vehicle positioning tracking method and device based on passive perception and readable medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BR112014027631A2 (en) * | 2012-05-04 | 2019-05-14 | Rearden, Llc | multi antenna (but) and multi-user (mu) system and method |
| CN104390693B (en) * | 2013-12-20 | 2018-08-21 | 上海波汇科技股份有限公司 | Link self diagnosis long-distance distributed optical fiber vibration monitors system |
| GB201519202D0 (en) * | 2015-10-30 | 2015-12-16 | Optasense Holdings Ltd | Monitoring traffic flow |
| CN107591002B (en) * | 2017-09-21 | 2020-06-02 | 电子科技大学 | Real-time estimation method for highway traffic parameters based on distributed optical fiber |
| CN107917738B (en) * | 2017-12-26 | 2020-01-03 | 南京大学（苏州）高新技术研究院 | Distributed optical fiber sensing system capable of simultaneously measuring temperature, strain and vibration |
-
2020
- 2020-07-08 CN CN202010652545.6A patent/CN111540212B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111540212A (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111540212B (en) | Highway interference estimation system and method for distributed optical fiber | |
| US11468667B2 (en) | Distributed intelligent traffic informatics using fiber sensing | |
| US11170639B2 (en) | Transportation threat detection system | |
| CN104200687A (en) | Driver speed control behavior monitoring device and method | |
| CN113763740A (en) | Big data traffic guidance system and guidance method | |
| CN112749210B (en) | Vehicle collision recognition method and system based on deep learning | |
| Rajab et al. | Vehicle classification and accurate speed calculation using multi-element piezoelectric sensor | |
| CN110852542B (en) | Road flatness calculation method and system | |
| CN108490163B (en) | Road defect detection equipment, detection vehicle, detection system and detection method | |
| JP2023550091A (en) | Vertical distance prediction of vibrations using distributed fiber optic sensing | |
| JP2024507530A (en) | Distributed fiber optic sensing system, apparatus, and method | |
| CN114235082B (en) | Intelligent metering method based on sand production monitoring system | |
| An et al. | Lane-based traffic arrival pattern estimation using license plate recognition data | |
| CN117151513A (en) | Method, device, equipment and storage medium for evaluating traffic safety | |
| JP7156502B2 (en) | Structural deterioration detection system and structure deterioration detection method | |
| EP4352649A1 (en) | Multi-dimensional modeling of driver and environment characteristics | |
| Liu et al. | Developments and applications of simulation-based online travel time prediction system: traveling to Ocean City, Maryland | |
| Sebestyen et al. | Road quality evaluation with mobile devices | |
| CN112927516B (en) | Road vehicle monitoring method, electronic equipment and storage medium | |
| RU2733061C1 (en) | System for monitoring condition of road, control and traffic management and method of operation of said system | |
| Struţu et al. | Accelerometer based road defects identification system | |
| CN113178072A (en) | Traffic anti-blocking prediction system and prediction method | |
| CN108039048B (en) | Traffic flow monitoring method | |
| Khoury et al. | Performance comparison of automatic vehicle identification and inductive loop traffic detectors for incident detection | |
| Sajal et al. | Cost-Effective Vehicle Monitoring System for Detecting Unacceptable Driver Behaviors on Road |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231222 Address after: No. 1751 Binsheng Road, Binjiang District, Hangzhou City, Zhejiang Province, 310000 Patentee after: Zhejiang Provincial Natural Gas Development Co.,Ltd. Patentee after: ZHEJIANG ENERGY GROUP CO.,LTD. Patentee after: ZHEJIANG University Address before: Zheneng second building, 1751 Binsheng Road, Binjiang District, Hangzhou City, Zhejiang Province 310052 Patentee before: ZHEJIANG ZHENENG NATURAL GAS OPERATION CO.,LTD. Patentee before: ZHEJIANG ENERGY GROUP CO.,LTD. Patentee before: ZHEJIANG University |