CN109409546A - Expressway Property manages and protects method - Google Patents
Expressway Property manages and protects method Download PDFInfo
- Publication number
- CN109409546A CN109409546A CN201811512256.5A CN201811512256A CN109409546A CN 109409546 A CN109409546 A CN 109409546A CN 201811512256 A CN201811512256 A CN 201811512256A CN 109409546 A CN109409546 A CN 109409546A
- Authority
- CN
- China
- Prior art keywords
- road
- vehicle
- inspection
- information
- produces
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/65—Control of camera operation in relation to power supply
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
Abstract
The invention discloses Expressway Properties to manage and protect method, comprising the following steps: according to patrol task, the vehicle-mounted camera for opening car-mounted device, which produces inspection road, to be shot；By shooting to inspection road produce image and be uploaded to server；Server is identified and is judged to described image, is gone wrong when judging that is produced from inspection road, and server control unmanned plane goes to corresponding inspection road presentation to set and carries out supplement shooting.The present invention is uploaded by the inspection road production shot to vehicle-mounted camera and automatic identification, and it is that control unmanned plane progress retake is taken the photograph going wrong, solves the problems, such as that the prior art is inconvenient using shooting by hand, roof establishing shot data acquisition is inaccurate and needs desk checking inconvenient.
Description
Technical field
Management domain is produced the present invention relates to road more particularly to a kind of Expressway Property manages and protects method.
Background technique
Implement road to produce management to be mainly to be responsible for by highway highway law enforcement department, by patrolling daily, satisfies the need and produce feelings
Condition is monitored, and all kinds of damages, theft are reconnoitred and tracked.Main includes three aspects: the claim produced to accident damage road；
(public security department's cooperation) is traced and claimed damages to theft road production case；It is damaged caused by producing Natural Damage, harsh weather all kinds of roads
It is bad, maintenance department is notified in time.Road, which produces, can be divided into means of transportation and affiliated facility, mainly road surface, roadbed, guardrail board, greening
Facility, traffic sign, charge station's facility etc..
The prior art has the following problems road production inspection: (1) reaching road presentation every time and set, by manually carrying out hand
Dynamic shooting, not only needs shut-down operation also to need additional manpower (driver and photographer at least two)；Or by roof
The camera that fixed angle is arranged carries out road and produces shooting, however has different height since is produced from different roads, so if adopting
It can make the problem of photographed data inaccuracy with the camera of equal angular；(2) inspection road produces image needs and is manually identified,
It is very troublesome to judge whether there is no problem.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of Expressway Properties to manage and protect method.
The purpose of the present invention is achieved through the following technical solutions: Expressway Property manages and protects method, including following
Step:
According to patrol task, the vehicle-mounted camera for opening car-mounted device, which produces inspection road, to be shot；
By shooting to inspection road produce image and be uploaded to server；
Server is identified and is judged to described image, is gone wrong when judging that is produced from inspection road, server controls nobody
Machine goes to corresponding inspection road presentation to set and carries out supplement shooting.
Further, the patrol task includes that inspection route and inspection road produce, and it includes that road production is fixed that the inspection road, which produces,
Position information, road produce trackside information, road produces elevation information；The server includes database, includes that road produces type, road for storing
Produce location information, road produces trackside information, the inspection road including road production elevation information produces information.
Further, the unlatching vehicle-mounted camera, which produces inspection road shoot, includes:
Location information and the vehicle real-time positioning information are produced according to the road, controls unlatching and the pass of vehicle-mounted camera
It closes；Simultaneously when controlling vehicle-mounted camera unlatching, the level side of trackside information control vehicle-mounted camera is produced according to the road
To rotation angle, angle is rotated according to the vertical direction that the road produces elevation information control vehicle-mounted camera；
It is described by shooting to inspection road produce image and be uploaded to server and include:
It will be uploaded after the image that the vehicle-mounted camera of control is shot produces location information binding with road.
Further, the server carries out identification to described image and judges to include judging that road produces trackside information and is produced from road
Whether whether correct, vehicle-mounted camera angle controls whether correct and needs repairing for judging that is produced from inspection road elevation information.
Further, the server is identified and is judged to described image, is rolled up using multiple trained depth
Product neural network model realizes that data are extracted, and each depth convolutional neural networks model corresponds to different types of inspection road and produces；
After getting upload data, is produced in location information acquisition database according to the road uploaded in data correspond to road first
The road for producing location information produces type；Producing type according to obtained road later selects corresponding depth convolutional neural networks model to carry out
Data are extracted and identification；Thinking that is produced from inspection road if output recognition result success is normal condition, otherwise it is assumed that go wrong,
And further judge road produce trackside information and road produce elevation information whether correct, vehicle-mounted camera angle control whether it is correct, with
And whether need repairing for judging that is produced from inspection road:
If continuous multiple identifications go wrong, then it is assumed that vehicle-mounted camera angle controls mistake, and to on-board crew
It gives a warning；If discontinuous multiple identifications go wrong, further judge to produce in image with the presence or absence of corresponding inspection road,
And if so, thinking that inspection road produces to need repairing to control unmanned plane corresponding inspection road presentation is gone to set carries out supplement shooting, if
There is no then thinking that road produces trackside information and/or road produces elevation information and exception occurs, the same unmanned plane that controls goes to corresponding inspection
Road presentation, which is set, carries out supplement shooting.
Further, the depth convolutional neural networks model includes sequentially connected: the first convolutional layer, volume Two
Lamination, the first down-sampling layer, the first residual error layer, third convolutional layer, the second down-sampling layer, the second residual error layer, Volume Four lamination,
Three down-sampling layers, third residual error layer and full articulamentum, each residual error layer include several residual units；
The training includes:
The inspection road of the corresponding types collected is produced image and is input to the depth convolutional Neural by S1, propagated forward
In network model, loss error is calculated；
S2, backpropagation will lose error update model parameter.
Further, the method also includes:
Patrol task is generated by management terminal and is sent to server；
It goes wrong when judging that is produced from inspection road, server is issued a notice information to management terminal.
Further, the car-mounted device includes:
Wireless communication module, for obtaining this patrol task；
Locating module, for generating vehicle real-time positioning information；
Vehicle-mounted camera is produced for shooting inspection road；
Control module is also used to for reading this patrol task and vehicle real-time positioning information according in patrol task
Inspection Route Generation respective routes prompt information, it is fixed in real time to be also used to produce location information and vehicle according to the road in patrol task
The opening and closing of position information control vehicle-mounted camera are also used to be produced when controlling the vehicle-mounted camera and opening according to the road
Trackside information, which controls the horizontal direction rotation angle of vehicle-mounted camera and produces elevation information according to the road, controls vehicle-mounted pick-up
The vertical direction of head rotates angle；
Route cue module, for showing the respective routes prompt information.
Further, the vehicle-mounted camera includes:
Optical lens produces image for shooting inspection road, and output end of image is connect with control module；
Longitudinal gear connects optical lens, for controlling the optical lens vertical direction rotation；
First servo motor, controlled end link control module, control terminal connect longitudinal gear, for controlling longitudinal gear rotation
Turn；
Transverse gear connects longitudinal gear, for controlling the rotation of optical lens horizontal direction by longitudinal gear；
Second servo motor, controlled end link control module, control terminal connect transverse gear, for controlling transverse gear rotation
Turn；
Camera power supply, for providing power supply to optical lens, first servo motor and the second servo motor；
Control switch, controlled end link control module, between camera power supply and points of common connection, the public company
Contact is the tie point of optical lens, first servo motor and the second servo motor three and camera power supply；
Shaking detection module, for detecting jitter conditions when vehicle-mounted camera is opened, output end is connect with control module,
For issuing warning information to control module when detecting the shake more than threshold value, so that is produced from the period collected inspection road
Image goes to corresponding inspection road presentation to set and carries out supplement shooting without judgement, server control unmanned plane.
Further, server control unmanned plane goes to corresponding inspection road presentation to set and carries out supplement to shoot including to unmanned plane
It is selected, comprising:
(1) select to produce the nearest unmanned plane of location information apart from road as the unmanned plane that goes to inspection road presentation to set；Or
(2) select that road is gone to produce the most fast unmanned plane of location information the unmanned plane to go to inspection road presentation to set；Or
(3) the optimal unmanned plane of power supply is selected as the unmanned plane that goes to inspection road presentation to set；Or
(4) idle unmanned plane is selected as the unmanned plane that goes to inspection road presentation to set.
The beneficial effects of the present invention are:
(1) present invention is produced by the inspection road shot to vehicle-mounted camera and carries out upload and automatic identification, and is being occurred
Problem is that control unmanned plane progress retake is taken the photograph, and solves the prior art and is obtained using shooting inconvenience, roof establishing shot data by hand
It takes inaccuracy and needs the problem of desk checking inconvenience.
(2) present invention produces location information, road production trackside information, road production elevation information by the road produced to inspection road and receives
Collect and issue, the angle of vehicle-mounted camera is adaptively adjusted to realize, solves the prior art and taken the photograph using fixed angle
As head progress road production inspection shooting so that the problem of data acquisition inaccuracy.
(3) present invention is extracted using multiple trained depth convolutional neural networks model realization data, each depth
Convolutional neural networks model corresponds to different types of inspection road and produces, to improve the accuracy of automatic identification.
(4) vehicle-mounted camera of the invention realizes angle adjustment by bi-motor, while being used for power saving by control switch
Operation avoids the whole of vehicle-mounted camera highway from opening, and picture photographing is unclear caused by also being avoided by shaking detection module because of shake
Erroneous judgement caused by clear.
Detailed description of the invention
Fig. 1 is the method for the present invention flow chart；
Fig. 2 is car-mounted device structural block diagram；
Fig. 3 is depth convolutional neural networks schematic diagram；
Fig. 4 is structure of vehicle-mounted CCD camera block diagram.
Specific embodiment
Technical solution of the present invention is clearly and completely described with reference to the accompanying drawing, it is clear that described embodiment
It is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that belong to "center", "upper", "lower", "left", "right", "vertical",
The direction of the instructions such as "horizontal", "inner", "outside" or positional relationship be based on direction or positional relationship described in attached drawing, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, belonging to " first ", " second " only
For descriptive purposes, it is not understood to indicate or imply relative importance.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, belong to " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
As long as in addition, the non-structure each other of technical characteristic involved in invention described below different embodiments
It can be combined with each other at conflict.
The present embodiment provides Expressway Properties to manage and protect method, solves the prior art using shooting inconvenience, roof by hand
Establishing shot data acquisition inaccuracy and the problem for needing desk checking inconvenience.
As shown in Figure 1, Expressway Property manages and protects method, comprising the following steps:
S1: according to patrol task, the vehicle-mounted camera for opening car-mounted device, which produces inspection road, to be shot.
Wherein, specifically, inspection route is inspection route as defined in higher level, can be also possible to for the route of Daily Round Check
The inspection route of specific condition；And inspection road produces and produces for the road on the inspection route, can be clapped on inspection route
It takes the photograph.
In addition, the patrol task includes that inspection route and inspection road produce, described in the preferred embodiment of the present embodiment
It includes that road produces location information, road produces trackside information, road produces elevation information that inspection road, which produces,；The server includes database, is used for
It stores the inspection road including road produces type, road produces location information, road produces trackside information, road produces elevation information and produces information.Its
In, it can be mileage information or GPS positioning information that it is the physical location that is produced from road that road, which produces location information, and road produces trackside information
For the wherein side in both sides of the road or it is connected across between two sides, and it is the practical height that is produced from the road that road, which produces elevation information,
Degree.
And the unlatching vehicle-mounted camera produces inspection road and shoots, there is a preferred embodiment, it is specific to wrap
It includes:
Location information and the vehicle real-time positioning information are produced according to the road, controls unlatching and the pass of vehicle-mounted camera
It closes；Simultaneously when controlling vehicle-mounted camera unlatching, the level side of trackside information control vehicle-mounted camera is produced according to the road
To rotation angle, angle is rotated according to the vertical direction that the road produces elevation information control vehicle-mounted camera.
Wherein, location information and the vehicle real-time positioning information are produced for the road, controls the unlatching of vehicle-mounted camera
And closing can be controlled in advance in a certain range in the present embodiment, i.e., according to two neighboring road produce between away from
From, when reach percent 80 apart from when, vehicle-mounted camera is carried out to the control of corresponding angle in advance.
More preferably, in the present embodiment, the vehicle-mounted camera includes two, is all set in vehicle roof, one of them
Inspection road for shooting vehicle heading produces image, is produced from another inspection road for being used to shoot vehicle driving opposite direction
Image.
That is one of vehicle-mounted camera shooting inspection road produces direct picture, another vehicle-mounted camera shoots inspection road
Produce back side image.
More preferably, as shown in Fig. 2, in the present embodiment, the car-mounted device includes:
Wireless communication module, for obtaining this patrol task；
Locating module, for generating vehicle real-time positioning information；
Vehicle-mounted camera is produced for shooting inspection road；
Control module is also used to for reading this patrol task and vehicle real-time positioning information according in patrol task
Inspection Route Generation respective routes prompt information, it is fixed in real time to be also used to produce location information and vehicle according to the road in patrol task
The opening and closing of position information control vehicle-mounted camera are also used to be produced when controlling the vehicle-mounted camera and opening according to the road
Trackside information, which controls the horizontal direction rotation angle of vehicle-mounted camera and produces elevation information according to the road, controls vehicle-mounted pick-up
The vertical direction of head rotates angle；
Route cue module, for showing the respective routes prompt information.
Wherein, wireless communication module can be 4G module, GPRS module etc.；And route cue module can show to touch
Screen or speech player.
S2: by shooting to inspection road produce image and be uploaded to server.
Specifically, in one of preferred embodiment of the present embodiment, it is described by shooting to inspection road produce on image
Reaching server includes:
It will be uploaded after the image that the vehicle-mounted camera of control is shot produces location information binding with road.
S3: server is identified and is judged to described image, is gone wrong when judging that is produced from inspection road, server controls nothing
It is man-machine to go to corresponding inspection road presentation to set to carry out supplement shooting.
And in the present embodiment, the server carries out identification to described image and judges to include judging that road produces trackside information
Producing elevation information with road, whether correct, vehicle-mounted camera angle controls whether correct and needs for judging that is produced from inspection road
It repairs.
That is, server satisfies the need automatically produces the acquisition and judgement of data, server judges according to the image got
The road produces whether be in normal condition.
Specifically, in the present embodiment, the server is identified and is judged to described image, using multiple by instructing
Experienced depth convolutional neural networks model realization data are extracted, and each depth convolutional neural networks model corresponds to different types of patrol
Road is examined to produce；
After getting upload data, is produced in location information acquisition database according to the road uploaded in data correspond to road first
The road for producing location information produces type；Producing type according to obtained road later selects corresponding depth convolutional neural networks model to carry out
Data are extracted and identification；Thinking that is produced from inspection road if output recognition result success is normal condition, otherwise it is assumed that go wrong,
And further judge road produce trackside information and road produce elevation information whether correct, vehicle-mounted camera angle control whether it is correct, with
And whether need repairing for judging that is produced from inspection road:
If continuous multiple identifications go wrong, then it is assumed that vehicle-mounted camera angle controls mistake, and to on-board crew
It gives a warning；If discontinuous multiple identifications go wrong, further judge to produce in image with the presence or absence of corresponding inspection road,
And if so, thinking that inspection road produces to need repairing to control unmanned plane corresponding inspection road presentation is gone to set carries out supplement shooting, if
There is no then thinking that road produces trackside information and/or road produces elevation information and exception occurs, the same unmanned plane that controls goes to corresponding inspection
Road presentation, which is set, carries out supplement shooting.
Specifically, corresponding type (street lamp, guideboard etc.) is produced due to being stored with each road in the database, in data
After passback, location information is produced according to the road uploaded in data and obtains the road production type for corresponding to road in database and producing location information, it
The corresponding depth convolutional neural networks model of selection for being output to corresponding types afterwards carries out data and extracts and identify.
And for specifically identifying, including following several situations:
(1) continuous multiple identifications go wrong, and will not be that multiple roads produce equipment while going wrong under normal conditions, because
This then thinks that the control of vehicle-mounted camera angle goes wrong；
(2) it individually goes wrong in identification, then further judges to produce in image with the presence or absence of corresponding inspection road:
(2-1) needs repairing if it is present thinking that is produced from inspection road；
(2-2) is if it does not exist, then think that road produces trackside information and/or road produces elevation information and exception occurs.
In addition, more preferably, in the present embodiment, as shown in figure 3, the depth convolutional neural networks model includes suitable
Secondary connection: the first convolutional layer, the second convolutional layer, the first down-sampling layer, the first residual error layer, third convolutional layer, the second down-sampling
Layer, the second residual error layer, Volume Four lamination, third down-sampling layer, third residual error layer and full articulamentum, if each residual error layer includes
Dry residual unit；
The training includes:
The inspection road of the corresponding types collected is produced image and is input to the depth convolutional neural networks by propagated forward
In model, loss error is calculated；
Backpropagation will lose error update model parameter.
Wherein, it for depth convolutional neural networks model, needs to carry out multilevel image data and is trained, that is, it is a large amount of right to need
The inspection road of type is answered to produce image；Data control is just carried out after the completion of training.
More preferably, in the present embodiment, the method also includes:
S0: patrol task is generated by management terminal and is sent to server；
Meanwhile in S3, go wrong when judging that is produced from inspection road, server is issued a notice information to management terminal.
Wherein, which can be handheld portable mobile intelligent terminal, be also possible to the fixed terminals such as PC machine.
More preferably, in the present embodiment, as shown in figure 4, the vehicle-mounted camera includes:
Optical lens produces image for shooting inspection road, and output end of image is connect with control module；
Longitudinal gear connects optical lens, for controlling the optical lens vertical direction rotation；
First servo motor, controlled end link control module, control terminal connect longitudinal gear, for controlling longitudinal gear rotation
Turn；
Transverse gear connects longitudinal gear, for controlling the rotation of optical lens horizontal direction by longitudinal gear；
Second servo motor, controlled end link control module, control terminal connect transverse gear, for controlling transverse gear rotation
Turn；
Camera power supply, for providing power supply to optical lens, first servo motor and the second servo motor；
Control switch, controlled end link control module, between camera power supply and points of common connection, the public company
Contact is the tie point of optical lens, first servo motor and the second servo motor three and camera power supply；
Shaking detection module, for detecting jitter conditions when vehicle-mounted camera is opened, output end is connect with control module,
For issuing warning information to control module when detecting the shake more than threshold value, so that is produced from the period collected inspection road
Image goes to corresponding inspection road presentation to set and carries out supplement shooting without judgement, server control unmanned plane.
Since inspection road presentation is in highway two sides, and production of not going the same way has different height, therefore watches by first
Taking motor drives longitudinal gear and the second servo motor to drive transverse gear, to the vertical direction of optical lens and level side
To angle be adjusted.
And control switch is used for power-save operation, i.e., when vehicle is located at position location (or predicted point), control module control
Control switch processed is opened, so that optical lens, first servo motor and the second servo motor be connected, the whole process of highway is avoided to open
It opens.
For shaking detection module, jitter conditions are detected for detecting when vehicle-mounted camera is opened, if super detecting
Warning information is issued to control module when crossing the shake of threshold value, so that the period collected inspection road produces image without sentencing
It is disconnected, avoid erroneous judgement caused by causing picture photographing unintelligible because of shake.
More preferably, in the present embodiment, server control unmanned plane goes to corresponding inspection road presentation to set and carries out supplement shooting
Including selecting unmanned plane, comprising:
(1) select to produce the nearest unmanned plane of location information apart from road as the unmanned plane that goes to inspection road presentation to set；Or
(2) select that road is gone to produce the most fast unmanned plane of location information the unmanned plane to go to inspection road presentation to set；Or
(3) the optimal unmanned plane of power supply is selected as the unmanned plane that goes to inspection road presentation to set；Or
(4) idle unmanned plane is selected as the unmanned plane that goes to inspection road presentation to set.
Obviously, the above embodiments are merely examples for clarifying the description, and does not limit the embodiments, right
For those of ordinary skill in the art, can also make on the basis of the above description other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And thus amplify out it is obvious variation or
It changes still within the protection scope of the invention.
Claims (10)
1. Expressway Property manages and protects method, it is characterised in that: the following steps are included:
According to patrol task, the vehicle-mounted camera for opening car-mounted device, which produces inspection road, to be shot；
By shooting to inspection road produce image and be uploaded to server；
Server is identified and is judged to described image, is gone wrong when judging that is produced from inspection road, before server controls unmanned plane
It is set toward corresponding inspection road presentation and carries out supplement shooting.
2. according to the method described in claim 1, it is characterized by: the patrol task includes that inspection route and inspection road produce,
It includes that road produces location information, road produces trackside information, road produces elevation information that the inspection road, which produces,；The server includes data
Library is produced for storing the inspection road including road produces type, road produces location information, road produces trackside information, road produces elevation information
Information.
3. according to the method described in claim 2, it is characterized by: the unlatching vehicle-mounted camera shoots the production of inspection road
Include:
Location information and the vehicle real-time positioning information are produced according to the road, controls the opening and closing of vehicle-mounted camera；Together
When control the vehicle-mounted camera open when, according to the road produce trackside information control vehicle-mounted camera horizontal direction rotate
Angle rotates angle according to the vertical direction that the road produces elevation information control vehicle-mounted camera；
It is described by shooting to inspection road produce image and be uploaded to server and include:
It will be uploaded after the image that the vehicle-mounted camera of control is shot produces location information binding with road.
4. according to the method in claim 2 or 3, it is characterised in that: the server is identified and sentenced to described image
It is disconnected include judge road produce trackside information and road produce elevation information whether correct, vehicle-mounted camera angle control whether correctly and
Whether need repairing for judging that is produced from inspection road.
5. according to the method described in claim 4, it is characterized by: the server is identified and is judged to described image,
It is extracted using multiple trained depth convolutional neural networks model realization data, each depth convolutional neural networks model pair
Different types of inspection road is answered to produce；
After getting upload data, produces location information according to the road uploaded in data first and obtain to correspond to road in database and produce and determine
The road of position information produces type；Producing type according to obtained road later selects corresponding depth convolutional neural networks model to carry out data
It extracts and identifies；Thinking that is produced from inspection road if output recognition result success is that normal condition is gone forward side by side otherwise it is assumed that going wrong
One step judges whether correct, vehicle-mounted camera angle controls whether correct, Yi Jiyong for road production trackside information and road production elevation information
Whether need repairing in judging that is produced from inspection road:
If continuous multiple identifications go wrong, then it is assumed that vehicle-mounted camera angle controls mistake, and issues to on-board crew
Warning；If discontinuous multiple identifications go wrong, further judge to produce in image with the presence or absence of corresponding inspection road, if
Supplement shooting is carried out in the presence of then thinking that inspection road produces to need repairing to control unmanned plane corresponding inspection road presentation is gone to set, if do not deposited
Then thinking that road produces trackside information and/or road produces elevation information and exception occurs, the same unmanned plane that controls goes to corresponding inspection road to produce
Position carries out supplement shooting.
6. according to the method described in claim 5, it is characterized by: the depth convolutional neural networks model includes sequentially
Connection: the first convolutional layer, the second convolutional layer, the first down-sampling layer, the first residual error layer, third convolutional layer, the second down-sampling layer,
Second residual error layer, Volume Four lamination, third down-sampling layer, third residual error layer and full articulamentum, each residual error layer include several
A residual unit；
The training includes:
The inspection road of the corresponding types collected is produced image and is input to the depth convolutional neural networks by S1, propagated forward
In model, loss error is calculated；
S2, backpropagation will lose error update model parameter.
7. according to the method described in claim 1, it is characterized by: the method also includes:
Patrol task is generated by management terminal and is sent to server；
It goes wrong when judging that is produced from inspection road, server is issued a notice information to management terminal.
8. according to the method described in claim 3, it is characterized by: the car-mounted device includes:
Wireless communication module, for obtaining this patrol task；
Locating module, for generating vehicle real-time positioning information；
Vehicle-mounted camera is produced for shooting inspection road；
Control module is also used to for reading this patrol task and vehicle real-time positioning information according to patrolling in patrol task
Route Generation respective routes prompt information is examined, is also used to produce location information according to the road in patrol task and vehicle positions letter in real time
The opening and closing of breath control vehicle-mounted camera are also used to produce trackside according to the road when controlling the vehicle-mounted camera and opening
Information controls the horizontal direction rotation angle of vehicle-mounted camera and produces elevation information control vehicle-mounted camera according to the road
Vertical direction rotates angle；
Route cue module, for showing the respective routes prompt information.
9. according to the method described in claim 8, it is characterized by: the vehicle-mounted camera includes:
Optical lens produces image for shooting inspection road, and output end of image is connect with control module；
Longitudinal gear connects optical lens, for controlling the optical lens vertical direction rotation；
First servo motor, controlled end link control module, control terminal connect longitudinal gear, for controlling longitudinal gear rotation；
Transverse gear connects longitudinal gear, for controlling the rotation of optical lens horizontal direction by longitudinal gear；
Second servo motor, controlled end link control module, control terminal connect transverse gear, for controlling transverse gear rotation；
Camera power supply, for providing power supply to optical lens, first servo motor and the second servo motor；
Control switch, controlled end link control module, between camera power supply and points of common connection, the points of common connection
For optical lens, the tie point of first servo motor and the second servo motor three and camera power supply；
Shaking detection module, for detecting jitter conditions when vehicle-mounted camera is opened, output end is connect with control module, is used for
Warning information is issued to control module when detecting the shake more than threshold value, so that the period collected inspection road produces image
Without judgement, server control unmanned plane goes to corresponding inspection road presentation to set and carries out supplement shooting.
10. according to the method described in claim 1, it is characterized by: server control unmanned plane goes to corresponding inspection road presentation
Setting and carrying out supplement shooting includes selecting unmanned plane, comprising:
(1) select to produce the nearest unmanned plane of location information apart from road as the unmanned plane that goes to inspection road presentation to set；Or
(2) select that road is gone to produce the most fast unmanned plane of location information the unmanned plane to go to inspection road presentation to set；Or
(3) the optimal unmanned plane of power supply is selected as the unmanned plane that goes to inspection road presentation to set；Or
(4) idle unmanned plane is selected as the unmanned plane that goes to inspection road presentation to set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811512256.5A CN109409546B (en) | 2018-12-11 | 2018-12-11 | Highway road production management and protection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811512256.5A CN109409546B (en) | 2018-12-11 | 2018-12-11 | Highway road production management and protection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109409546A true CN109409546A (en) | 2019-03-01 |
| CN109409546B CN109409546B (en) | 2020-11-17 |
Family
ID=65458449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811512256.5A Active CN109409546B (en) | 2018-12-11 | 2018-12-11 | Highway road production management and protection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109409546B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111178743A (en) * | 2019-12-25 | 2020-05-19 | 中国人民解放军军事科学院国防科技创新研究院 | Method for autonomous cooperative observation and cooperative operation of unmanned aerial vehicle cluster |
| CN115225814A (en) * | 2022-06-17 | 2022-10-21 | 苏州蓝博控制技术有限公司 | Camera assembly and video processing method thereof |
| CN116012611A (en) * | 2022-12-28 | 2023-04-25 | 北京道仪数慧科技有限公司 | Road product detection method and carrier |
| CN117391911A (en) * | 2023-12-08 | 2024-01-12 | 日照先森网络科技股份有限公司 | Smart city comprehensive management method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778681A (en) * | 2014-01-24 | 2014-05-07 | 青岛秀山移动测量有限公司 | Vehicle-mounted high-speed road inspection system and data acquisition and processing method |
| CN105049812A (en) * | 2015-08-07 | 2015-11-11 | 清华大学深圳研究生院 | Unmanned aerial vehicle portable ground station processing method and system |
| JP2015223995A (en) * | 2014-05-29 | 2015-12-14 | 株式会社熊谷組 | Unmanned flight body for photographing |
| CN105389988A (en) * | 2015-12-07 | 2016-03-09 | 北京航空航天大学 | Multi-unmanned aerial vehicle cooperation highway intelligent inspection system |
| US20160078759A1 (en) * | 2012-08-06 | 2016-03-17 | Cloudparc, Inc. | Tracking a Vehicle Using an Unmanned Aerial Vehicle |
| CN105549613A (en) * | 2015-12-11 | 2016-05-04 | 北京恒华伟业科技股份有限公司 | Automatic inspection method and automatic inspection device based on unmanned aerial vehicle |
| CN107193027A (en) * | 2017-05-27 | 2017-09-22 | 山东交通职业学院 | A kind of highway UAV Intelligent inspection alignment system |
| US20180265296A1 (en) * | 2017-03-16 | 2018-09-20 | Amazon Technologies, Inc. | Demand-based distribution of items using intermodal carriers and unmanned aerial vehicles |
| CN108831157A (en) * | 2018-07-27 | 2018-11-16 | 中山火炬高新企业孵化器有限公司 | A kind of garden security protection based on intelligent robot is deployed to ensure effective monitoring and control of illegal activities management system |
-
2018
- 2018-12-11 CN CN201811512256.5A patent/CN109409546B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160078759A1 (en) * | 2012-08-06 | 2016-03-17 | Cloudparc, Inc. | Tracking a Vehicle Using an Unmanned Aerial Vehicle |
| US20180137356A1 (en) * | 2012-08-06 | 2018-05-17 | Cloudparc, Inc. | Tracking a vehicle using an unmanned aerial vehicle |
| CN103778681A (en) * | 2014-01-24 | 2014-05-07 | 青岛秀山移动测量有限公司 | Vehicle-mounted high-speed road inspection system and data acquisition and processing method |
| JP2015223995A (en) * | 2014-05-29 | 2015-12-14 | 株式会社熊谷組 | Unmanned flight body for photographing |
| CN105049812A (en) * | 2015-08-07 | 2015-11-11 | 清华大学深圳研究生院 | Unmanned aerial vehicle portable ground station processing method and system |
| CN105389988A (en) * | 2015-12-07 | 2016-03-09 | 北京航空航天大学 | Multi-unmanned aerial vehicle cooperation highway intelligent inspection system |
| CN105549613A (en) * | 2015-12-11 | 2016-05-04 | 北京恒华伟业科技股份有限公司 | Automatic inspection method and automatic inspection device based on unmanned aerial vehicle |
| US20180265296A1 (en) * | 2017-03-16 | 2018-09-20 | Amazon Technologies, Inc. | Demand-based distribution of items using intermodal carriers and unmanned aerial vehicles |
| CN107193027A (en) * | 2017-05-27 | 2017-09-22 | 山东交通职业学院 | A kind of highway UAV Intelligent inspection alignment system |
| CN108831157A (en) * | 2018-07-27 | 2018-11-16 | 中山火炬高新企业孵化器有限公司 | A kind of garden security protection based on intelligent robot is deployed to ensure effective monitoring and control of illegal activities management system |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111178743A (en) * | 2019-12-25 | 2020-05-19 | 中国人民解放军军事科学院国防科技创新研究院 | Method for autonomous cooperative observation and cooperative operation of unmanned aerial vehicle cluster |
| CN115225814A (en) * | 2022-06-17 | 2022-10-21 | 苏州蓝博控制技术有限公司 | Camera assembly and video processing method thereof |
| CN115225814B (en) * | 2022-06-17 | 2023-09-05 | 苏州蓝博控制技术有限公司 | Camera assembly and video processing method thereof |
| CN116012611A (en) * | 2022-12-28 | 2023-04-25 | 北京道仪数慧科技有限公司 | Road product detection method and carrier |
| CN116012611B (en) * | 2022-12-28 | 2023-09-01 | 北京道仪数慧科技有限公司 | Road product detection method and carrier |
| CN117391911A (en) * | 2023-12-08 | 2024-01-12 | 日照先森网络科技股份有限公司 | Smart city comprehensive management method and system |
| CN117391911B (en) * | 2023-12-08 | 2024-02-27 | 日照先森网络科技股份有限公司 | Smart city comprehensive management method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109409546B (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109614931A (en) | Vehicle-mounted road produces inspection management-control method and system | |
| CN109409546A (en) | Expressway Property manages and protects method | |
| CN107792261B (en) | Management system for intelligently identifying vehicle parking environment through detection and identification equipment | |
| CN105809797B (en) | Video camera and parking ground control system for parking ground control system | |
| CN102542806B (en) | Real-time monitoring system for license plate shielding of vehicles running on speedway and control method thereof | |
| CN105931384B (en) | Self-service pick-up method during vehicle sharing and the vehicle sharing method based on self-service pick-up | |
| CN208014185U (en) | A kind of Roadside Parking monitoring system based on high-order image recognition and ETC equipment | |
| CN105931471A (en) | Rule and regulation pre-violation warning system in vehicle sharing process and vehicle sharing method based on rule and regulation pre-violation warning system in vehicle sharing process | |
| CN108765976A (en) | The parallel parking information of trackside manages system and method | |
| CN107784739B (en) | Self-service car returning method in video-based vehicle sharing process and self-service car returning-based vehicle sharing method | |
| CN101536043A (en) | A method for road charging, road information and parking charging and navigation and the system thereof | |
| CN103295402A (en) | Intelligent traffic overspeed snapshot system | |
| CN108986539A (en) | Parking management system, method, vehicle information collecting device and management server | |
| CN105427619A (en) | Vehicle following distance automatic recording system and method | |
| CN106023461A (en) | Self-service car-returning method during car sharing process based on appointed positions and car-sharing method based on self-service car-returning | |
| CN107784405A (en) | A kind of vehicle based on real-time video share during self-service returning method and based on the self-service vehicle sharing method returned the car | |
| CN106585530A (en) | Vehicle-mounted snapshooting device and control method thereof | |
| CN108664905A (en) | A kind of Roadside Parking management method, system and device based on infrared image | |
| CN107786830A (en) | A kind of vehicle based on video share during self-service pick-up method and vehicle sharing method based on self-service pick-up | |
| CN208196816U (en) | A kind of oilfield stations well site inspection intelligent robot system | |
| CN106251627A (en) | A kind of vehicular break in traffic rules and regulations intelligent monitoring device | |
| CN105118301A (en) | Vehicle-mounted law violation monitoring system | |
| CN107564295A (en) | Intelligence checks the control method for system of deploying to ensure effective monitoring and control of illegal activities | |
| CN109639966A (en) | Vehicle-mounted control method based on Asset supervision | |
| CN206021373U (en) | A kind of monitoring device of recognizable alert |
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 |