CN210262620U - Highway road surface state detecting system based on vehicle event data recorder - Google Patents
Highway road surface state detecting system based on vehicle event data recorder Download PDFInfo
- Publication number
- CN210262620U CN210262620U CN201920675726.3U CN201920675726U CN210262620U CN 210262620 U CN210262620 U CN 210262620U CN 201920675726 U CN201920675726 U CN 201920675726U CN 210262620 U CN210262620 U CN 210262620U
- Authority
- CN
- China
- Prior art keywords
- data recorder
- road surface
- vehicle
- automobile data
- inspection
- 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
Images
Abstract
The utility model discloses a road surface state detection system based on a vehicle event data recorder, which comprises a system main body and a plurality of inspection vehicles; the system main body comprises a platform server and a monitoring center management platform; each inspection vehicle is provided with an inspection vehicle automobile data recorder; each inspection vehicle automobile data recorder comprises a main control unit, a camera and a touch screen display; the main control unit is respectively connected with the camera and the touch screen display, and the camera is used for acquiring images of the road surface; the monitoring center management platform utilizes a plurality of pictures and a deep learning algorithm based on a convolutional neural network to automatically identify the damage state of the road surface, and simultaneously utilizes the positioning data and the GIS map of each inspection vehicle and automobile data recorder to analyze and display. The utility model discloses the picture that degree of depth learning algorithm can make full use of vehicle event data recorder collection based on convolution neural network realizes the damaged situation automatic identification on road surface.
Description
Technical Field
The utility model relates to a road detection technology field, in particular to highway road surface state detecting system based on vehicle event data recorder.
Background
With the rapid increase of highway mileage in China, the workload of maintenance management such as highway patrol and the like is continuously increased, and the requirement on highway detection is increasingly greater. Road surface detection can acquire road surface road condition information, can judge the road surface damage degree through road condition information, provides important basis for the maintenance and the reconstruction of highway. The pavement damage inspection and early warning mainly collects the types and damage degrees of pavement diseases through a photographing and video recording technology, and then identifies and reads the damage condition of the pavement through a picture identification technology, so as to complete the rapid quantitative analysis of the pavement damage condition.
The french development developed a pavement photographic vehicle (gerpso) which was first used for identifying pavement diseases. Subsequently, other countries have successively studied automatic identification technologies for road surface diseases based on the needs of the road surface damage detection in this country, and have developed many automatic detection and identification instruments for road surface damage. However, the cost of the road surface photography inspection vehicle is high, and generally only after the road surface photography inspection vehicle collects the road surface, the road surface photography inspection vehicle can perform post analysis by using special software, so that the road surface damage inspection is mostly performed by adopting a manual/semi-manual inspection mode at present. In 2012, the Alex Krizhevsky team reduces the picture recognition and classification error records from 26% to 15% in the ImageNet challenge race by virtue of the convolutional neural network, thereby greatly improving the classification level of pictures. Many researchers apply deep learning to road surface damage detection, and a good detection effect is achieved.
In order to guarantee driving safety, more and more drivers install the automobile data recorder on the windshield, and according to statistics, the sales volume of the automobile data recorder breaks through tens of millions of automobiles every year in recent years, and road traffic and driving conditions are recorded. However, most recorded pictures are 'deep and asleep' in the card, and can be taken out only when accidents happen.
In the prior art, some of the published patents also use a drive recorder for road traffic management, but the use of drive recorder picture data for road surface damage detection has not been found. Such as: the utility model patent with publication number CN 105046951 a, vehicle monitoring method and module based on driving recorder, realizes the storage of driving video in abnormal time period, and provides reliable basis for the subsequent traffic accident treatment.
For another example: the utility model patent with publication number CN 207008863U is a road traffic monitoring system based on vehicle event data recorder, and each vehicle that is equipped with vehicle event data recorder is regarded as "traffic police cruiser", reduces the traffic accident probability, saves a large amount of manpower and materials, improves emergency rate of disposition.
Therefore, in order to fully utilize the pictures and the GPS data of the automobile data recorder, a road surface state detection system based on an image recognition technology and fully utilizing the pictures acquired by the automobile data recorder needs to be developed.
SUMMERY OF THE UTILITY MODEL
In view of the above defects in the prior art, the utility model provides a highway pavement state detection system based on vehicle event data recorder, one of the purposes that realizes is that the picture that vehicle event data recorder gathered can be fully utilized to the deep learning algorithm based on convolutional neural network, realizes the damaged condition automatic identification of road surface; the satellite positioning data of the automobile data recorder and the GIS map are fully utilized, and the GIS map real-time display and alarm of the automobile data recorder picture are realized.
In order to achieve the above object, the utility model discloses a highway road surface state detecting system based on vehicle event data recorder, including system's main part and a plurality of inspection car.
The system main body comprises a platform server and a monitoring center management platform;
each inspection vehicle is provided with an inspection vehicle automobile data recorder;
each inspection vehicle automobile data recorder comprises a main control unit, a camera and a touch screen display;
the main control unit is respectively connected with the camera and the touch screen display, images of the road surface are collected by the camera, and the running state and the control instruction are displayed by the touch screen display;
each inspection vehicle automobile data recorder is connected with a GPS system or a Beidou through a GPS/Beidou receiving module;
each patrol and examine car vehicle event data recorder all relies on 3G, 4G and wiFi communication module, according to different networks automatic selection communication type to through 3G wireless network, 4G wireless network or wiFi wireless network with the platform server is connected.
Preferably, each patrol and examine the car and all be equipped with vehicle mounted power, vehicle mounted power to corresponding patrol and examine car vehicle event data recorder power supply.
Preferably, each automobile data recorder of the inspection vehicle is provided with a Micro SD memory card, and the images and the operation records are stored by the Micro SD memory card.
Preferably, the main control unit comprises a MT8382 type 4-core 1.3GHz processor.
The utility model has the advantages that:
the utility model discloses a picture that vehicle event data recorder gathered can make full use of by the deep learning algorithm of convolution neural network, realize the damaged situation automatic identification of road surface; the satellite positioning data of the automobile data recorder and the GIS map are fully utilized, and the GIS map real-time display and alarm of the automobile data recorder picture are realized.
The utility model solves the problems that the prior art is high in cost for the road surface photography detection vehicle, and generally only can use special software to perform post analysis after the collection; each highway patrol and inspection vehicle provided with the automobile data recorder is changed into a highway pavement maintenance and inspection vehicle, so that the problem that manual/semi-manual patrol and inspection of the current highway pavement damage state wastes time and labor is solved, and support is provided for automatic patrol and alarm of the highway pavement damage.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings, so as to fully understand the objects, the features and the effects of the present invention.
Drawings
Fig. 1 shows a schematic structural diagram of an embodiment of the present invention.
Fig. 2 shows a schematic structural diagram of each of the automobile data recorders of the inspection vehicle in an embodiment of the present invention.
Fig. 3 shows a schematic diagram of a state of each of the inspection vehicle event data recorders, the platform server and the monitoring center management platform in an embodiment of the present invention.
Detailed Description
Examples
As shown in fig. 1 to 3, the road surface condition detection system based on the automobile data recorder comprises a system main body and a plurality of inspection vehicles.
The system main body comprises a platform server and a monitoring center management platform;
each inspection vehicle is provided with an inspection vehicle automobile data recorder;
each inspection vehicle automobile data recorder comprises a main control unit, a camera and a touch screen display;
the main control unit is respectively connected with the camera and the touch screen display, acquires an image of a road surface by the camera, displays an operation state by the touch screen display and receives a control instruction;
each inspection vehicle driving recorder is connected with a GPS system or a Beidou through a GPS/Beidou receiving module;
each patrol and examine car vehicle event data recorder all relies on 3G, 4G and wiFi communication module, according to different networks automatic selection communication type to through 3G wireless network, 4G wireless network or wiFi wireless network with the platform server is connected.
In actual use, the monitoring center management platform utilizes a plurality of pictures transmitted from the automobile data recorder through the 3G/4G/WiFi network, automatically identifies the damage state of the road surface based on a deep learning algorithm of a convolutional neural network, and simultaneously utilizes positioning data and a GIS map of each inspection vehicle automobile data recorder to analyze and display each picture based on the GIS map.
The principle of the utility model lies in that the pictures collected by the automobile data recorder can be fully utilized by the deep learning algorithm of the convolutional neural network, and the automatic identification of the damage condition of the road surface is realized; the satellite positioning data of the automobile data recorder and the GIS map are fully utilized, and the GIS map real-time display and alarm of the automobile data recorder picture are realized.
In some embodiments, each inspection vehicle is provided with a vehicle-mounted power supply, and the vehicle-mounted power supply supplies power to the corresponding inspection vehicle automobile data recorder.
In some embodiments, each inspection vehicle automobile data recorder is provided with a Micro SD memory card, and images and operation records are stored by the Micro SD memory card.
In certain embodiments, the master control unit includes a MT8382 type 4 core 1.3GHz processor.
The foregoing has described in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions that can be obtained by a person skilled in the art through logic analysis, reasoning or limited experiments based on the prior art according to the concepts of the present invention should be within the scope of protection defined by the claims.
Claims (4)
1. The highway pavement state detection system based on the automobile data recorder comprises a system main body and a plurality of inspection vehicles; the method is characterized in that:
the system main body comprises a platform server and a monitoring center management platform;
each inspection vehicle is provided with an inspection vehicle automobile data recorder;
each inspection vehicle automobile data recorder comprises a main control unit, a camera and a touch screen display;
the main control unit is respectively connected with the camera and the touch screen display, images of the road surface are collected by the camera, and the running state and the control instruction are displayed by the touch screen display;
each inspection vehicle automobile data recorder is connected with a GPS system or a Beidou through a GPS/Beidou receiving module;
each patrol and examine car vehicle event data recorder all relies on 3G, 4G and wiFi communication module, according to different networks automatic selection communication type to through 3G wireless network, 4G wireless network or wiFi wireless network with the platform server is connected.
2. The automobile data recorder-based road surface state detection system according to claim 1, wherein each patrol vehicle is provided with a vehicle-mounted power supply, and the vehicle-mounted power supply supplies power to the corresponding patrol vehicle automobile data recorder.
3. The automobile data recorder-based road surface state detection system according to claim 1, wherein each of the inspection vehicle automobile data recorders is provided with a Micro SD memory card, and the images and the operation records are stored by the Micro SD memory card.
4. The tachograph-based roadway surface condition detection system of claim 1, wherein the master control unit comprises a MT8382 type 4-core 1.3GHz processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201920675726.3U CN210262620U (en) | 2019-05-13 | 2019-05-13 | Highway road surface state detecting system based on vehicle event data recorder |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201920675726.3U CN210262620U (en) | 2019-05-13 | 2019-05-13 | Highway road surface state detecting system based on vehicle event data recorder |
Publications (1)
Publication Number | Publication Date |
---|---|
CN210262620U true CN210262620U (en) | 2020-04-07 |
Family
ID=70024509
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201920675726.3U Active CN210262620U (en) | 2019-05-13 | 2019-05-13 | Highway road surface state detecting system based on vehicle event data recorder |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN210262620U (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113724503A (en) * | 2021-08-31 | 2021-11-30 | 山东交通学院 | Automatic highway state inspection system and method based on cloud platform |
-
2019
- 2019-05-13 CN CN201920675726.3U patent/CN210262620U/en active Active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113724503A (en) * | 2021-08-31 | 2021-11-30 | 山东交通学院 | Automatic highway state inspection system and method based on cloud platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111932693B (en) | Urban road side parking lot management system | |
WO2018058958A1 (en) | Road vehicle traffic alarm system and method therefor | |
CN103723096B (en) | With the drive assist system of radio communication function | |
CN111105642A (en) | Intelligent parking lot parking management system and parking method | |
CN106056839A (en) | Security monitoring system and method for internet-based car hailing service | |
CN104599443A (en) | Vehicle-mounted forewarning terminal for driving behaviors based on information fusion and forewarning method thereof | |
WO2021223418A1 (en) | Parking detection method and apparatus employing visual difference | |
CN206164739U (en) | Automation video recording that vehicle far -reaching headlamp used is in violation of rules and regulations collected evidence and enforcement system | |
CN107067730B (en) | Network appointment vehicle-man-vehicle inconsistency monitoring method based on bayonet equipment | |
CN108133599A (en) | A kind of slag-soil truck video frequency identifying method and system | |
CN111739191A (en) | Violation early warning method, device, equipment and storage medium | |
CN105809969A (en) | Method and system for checking static vehicles | |
CN103268702A (en) | Method for obtaining evidence of illegal occupying of non-bus vehicles on bus lane | |
CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
CN114341962A (en) | Dangerous vehicle display system, dangerous vehicle display device, dangerous vehicle display program, computer-readable recording medium, and apparatus having recorded the program | |
CN210262620U (en) | Highway road surface state detecting system based on vehicle event data recorder | |
CN113436361A (en) | Roadside berth management system based on unmanned inspection vehicle | |
CN114005189A (en) | Parking charging method, device and system, parking management platform and storage medium | |
CN113723273A (en) | Vehicle track information determination method and device and computer equipment | |
CN111784859A (en) | Special embedded lane control system for expressway | |
CN112950942A (en) | Intelligent detection method for motor vehicle illegal parking based on video analysis | |
CN110909641A (en) | Method, device and system for detecting overload of motorcycle | |
CN113989715A (en) | Vehicle parking violation detection method and device, electronic equipment and storage medium | |
CN208411562U (en) | Cloud intelligent back vision mirror and the big-and-middle-sized automobile of 360 ° of monitoring | |
CN112489487A (en) | Street parking system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |