CN205862589U - A kind of automatic Vehicle Recognition System - Google Patents
A kind of automatic Vehicle Recognition System Download PDFInfo
- Publication number
- CN205862589U CN205862589U CN201620830907.5U CN201620830907U CN205862589U CN 205862589 U CN205862589 U CN 205862589U CN 201620830907 U CN201620830907 U CN 201620830907U CN 205862589 U CN205862589 U CN 205862589U
- Authority
- CN
- China
- Prior art keywords
- vehicle
- portal frame
- recognition system
- ring coil
- acquisition device
- 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.)
- Expired - Fee Related
Links
Abstract
A kind of automatic Vehicle Recognition System, including portal frame, ring coil detector, image acquisition device, laser scanner and data center, ring coil detector obtains the vehicle signal curve through out-of-date generation, image acquisition device obtains the video frame image of vehicle, laser scanner collects vehicle through out-of-date two-dimensional transversal cross section profile each point, all it is sent to data center, merges for the vehicle characteristic information that will obtain, identify vehicle.Ring coil detector, image acquisition device, laser scanner are arranged on the portal frame above track, and ring coil detector is layed in below track；This utility model is less by environmental effects such as light weather, information of vehicles is obtained, it is achieved multicharacteristic information merges, and can obtain vehicle shape, size characteristic accurately from picture, video, each orientation of laser scanning, carrying out rapidly data base's comparison, efficiency height identifies that error rate is low simultaneously.
Description
Technical field
The open a kind of automatic Vehicle Recognition System of this utility model.
Background technology
Existing traffic system is used for identify in the system of automobile, shoots merely automobile figure just with photographic head
Picture, is then passed through processing center and combines the picture integration of each different angles, finally piece together out the most complete automobile overall diagram
Condition, though this kind of method and system are relatively succinct, but affected by environment relatively big, such as severe weather conditions and night are time light is poor
Marquis, the quality of the image information acquired in photographic head is just difficult to ensure that, and when vehicle flowrate is bigger, occurs that car body is mutual unavoidably
Circumstance of occlusion, under analogue, identifies that the efficiency of system is just substantially reduced.
Utility model content
For solving above existing issue, this utility model provides a kind of automatic Vehicle Recognition System.
This utility model, for realizing object above, uses following scheme: a kind of automatic Vehicle Recognition System, including front terminal number
Processing layer according to acquisition layer, data transfer layer, data center, described front end data acquisition layer includes portal frame, Data mining
Device, image acquisition device, laser scanner, described portal frame is across above track, and described ring coil detector is layed in car
Below road, described image acquisition device is fixed in downwards above portal frame, and described image acquisition device main body is high-definition camera, described
Laser scanner is fixed on portal frame, and described data transfer layer includes switch, optical transmitter and receiver, and described data center processes layer bag
Include data center.
Preferably, the data message that described front end data acquisition layer collects is sent at data center through data transfer layer
Reason layer.
Preferably, described portal frame is crossed with some tracks.
Preferably, described ring coil detector includes that LC oscillating circuit and detector, described ring coil detector divide
It is not layed in below each bar track.
Preferably, the described image acquisition device of correspondence it is respectively and fixedly connected with above described some tracks on portal frame.
Preferably, described portal frame is evenly distributed with several described laser scanners.
The beneficial effect that this utility model produces: less by environmental effects such as light weather, sweeps from picture, video, laser
Retouch each orientation and obtain information of vehicles, it is achieved multicharacteristic information merges, and can obtain vehicle shape, size characteristic accurately, rapidly
Carrying out data base's comparison, efficiency height identifies that error rate is low simultaneously.
Accompanying drawing explanation
Fig. 1 is this model recognition system；
Fig. 2 is systematic schematic diagram；
In figure: 1, portal frame, 2, ring coil detector, 3, image acquisition device, 4, laser scanner, 5, data center.
Detailed description of the invention
Below in conjunction with the accompanying drawings the technical solution of the utility model is made specifically, complete explanation.
A kind of automatic Vehicle Recognition System, processes layer, institute including front end data acquisition layer, data transfer layer, data center
State front end data acquisition layer and include portal frame 1, ring coil detector 2, image acquisition device 3, laser scanner 4, described gantry
Frame 1 is across above track, and described ring coil detector 2 is layed in below track, and described image acquisition device 3 is fixed in downwards
Above portal frame 1, described laser scanner 4 is fixed on portal frame 1, and described data transfer layer includes switch, optical transmitter and receiver, institute
State data center's process layer and include data center 5.
The data message that described front end data acquisition layer collects is sent to data center through data transfer layer and processes layer；Institute
State portal frame 1 and be crossed with some tracks；Described ring coil detector 2 includes LC oscillating circuit and detector, described annular
Coil checker 2 is layed in below each bar track respectively；The institute of correspondence it is respectively and fixedly connected with on portal frame 1 above described some tracks
Stating image acquisition device 3, described image acquisition device 3 main body is made up of high-definition camera；It is evenly distributed with some on described portal frame 1
Individual described laser scanner 4.
Described ring coil detector 2, obtains vehicle through out-of-date produced signal curve；Described image acquisition device 3, obtains
Take the video frame image comprising vehicle；Described laser scanner 4, collects vehicle through out-of-date two-dimensional transversal cross section profile each point；
The vehicle characteristic information utilization of acquisition is included Point Cloud of Laser Scanner and regards by the data center 5 being positioned at data center's process layer
Frequently the registration technique of image, three-dimensional vehicle reconfiguration technique based on Point Cloud of Laser Scanner and video data, based on multiple features
The technology such as the vehicle cab recognition technology of information fusion carry out merging, processing, and reach to identify vehicle.
Embodiment, described automatic Vehicle Recognition System mainly includes two stages, systematic training stage and system test rank
Section.Before system formally comes into operation, first carry out systematic training study, the data that different sensors is collected, use
Code book under K-means algorithm construction respective sensor.Then by the sample vehicle spy that code book is generated under different sensors
Levy rectangular histogram and be sequentially configured to the feature histogram of, finally go to train a typical BP neutral net by these data；It is being
System test phase, for test vehicle, generates its feature histogram, then obtains vehicle cab recognition knot according to BP neural network classification
Really, through systematic training stage and system test stage, data center collects the master data information of various vehicle, for system
Work provides Information base.Described K-means algorithm is a kind of for calculating the algorithm that data are assembled, and described BP neutral net is
A kind of typical operation model.
Detailed process when system formally comes into operation is: when vehicle entrance is preset with the track of ring coil detector 2
During region, by the situation of change of the collected curve of ring coil detector 2, data center 5 can be determined that vehicle enters inspection
Survey region, control each sensor acquisition data: the chassis structure of different automobile types is different with ferromagnetic material distribution, and vehicle passes through simultaneously
The induction curve information cutting solenoid generation during ring coil detector 2 is sent to data center 5 through switch, in data
Generate corresponding feature histogram after the heart 5 reception information, provide foundation for vehicle classification；Meanwhile the laser of different azimuth is swept
Retouch instrument 4 to be scanned through vehicle from all angles, scanning collection to laser point cloud data be sent to data through switch
Center 5, data center 5 extracts the 3D shape constructed, and extracts the geometric properties information such as the height of vehicle, width and length,
And generate feature histogram；The video camera video image to comprising vehicle uses background subtraction to carry out foreground target detection, to inspection
The vehicle region measured is extracted its geometric parameter and is sent to data center 5 through switch and optical transmitter and receiver, before data center 5 extracts
The set feature information such as scene area area, boundary rectangle length generate individual features rectangular histogram simultaneously.Final data center 5 will be each
The information rectangular histogram that individual sensor receives collects, and connects and generates a total vehicle characteristics rectangular histogram, then that vehicle characteristics is straight
Side's figure gives trained BP neutral net, obtains the final recognition result of vehicle through data retrieval contrast.
Obviously, described embodiment is only a part of embodiment of the present utility model rather than whole embodiment.Base
Embodiment in this utility model, the institute that those of ordinary skill in the art are obtained under not making creative work premise
There is other to implement, broadly fall into protection scope of the present invention.
Claims (6)
1. an automatic Vehicle Recognition System, processes layer including front end data acquisition layer, data transfer layer, data center, and it is special
Levy and be: described front end data acquisition layer includes that portal frame (1), ring coil detector (2), image acquisition device (3), laser are swept
Retouching instrument (4), described portal frame (1) is across above track, and described ring coil detector (2) is layed in below track, described
Image acquisition device (3) is fixed in downwards portal frame (1) top, and described laser scanner (4) is fixed on portal frame (1), described
Data transfer layer includes switch, optical transmitter and receiver, and described data center processes layer and includes data center (5).
A kind of automatic Vehicle Recognition System, it is characterised in that: described front end data acquisition layer gathers
To data message through data transfer layer be sent to data center process layer.
A kind of automatic Vehicle Recognition System, it is characterised in that: described portal frame (1) is if being crossed with
Dry bar track.
A kind of automatic Vehicle Recognition System, it is characterised in that: described ring coil detector (2)
Being layed in below each bar track respectively, described ring coil detector (2) includes LC oscillating circuit and detector.
A kind of automatic Vehicle Recognition System, it is characterised in that: portal frame above described some tracks
(1) being respectively and fixedly connected with the image acquisition device (3) of correspondence on, described image acquisition device (3) main body is high-definition camera.
A kind of automatic Vehicle Recognition System, it is characterised in that: described portal frame (1) is upper uniformly to be divided
It is furnished with several described laser scanners (4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620830907.5U CN205862589U (en) | 2016-08-01 | 2016-08-01 | A kind of automatic Vehicle Recognition System |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620830907.5U CN205862589U (en) | 2016-08-01 | 2016-08-01 | A kind of automatic Vehicle Recognition System |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN205862589U true CN205862589U (en) | 2017-01-04 |
Family
ID=57654743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201620830907.5U Expired - Fee Related CN205862589U (en) | 2016-08-01 | 2016-08-01 | A kind of automatic Vehicle Recognition System |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN205862589U (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256636A (en) * | 2017-06-29 | 2017-10-17 | 段晓辉 | A kind of traffic flow acquisition methods for merging laser scanning and video technique |
| CN107505037A (en) * | 2017-07-05 | 2017-12-22 | 湖北鑫美企业发展股份有限公司 | A kind of supervising device that can finely identify vehicle |
| CN110470241A (en) * | 2019-08-19 | 2019-11-19 | 天津大学 | A kind of refractory brick curvature detection system and method based on structure light vision |
| CN110807936A (en) * | 2019-11-13 | 2020-02-18 | 佛山科学技术学院 | Statistical system for identifying vehicle model and measuring and calculating speed |
| CN112179307A (en) * | 2020-09-10 | 2021-01-05 | 上海交通大学 | Fuel cell metal bipolar plate forming error detection device |
| CN114202927A (en) * | 2021-12-27 | 2022-03-18 | 招商局重庆公路工程检测中心有限公司 | Vehicle type detection method based on multi-sensor fusion |
-
2016
- 2016-08-01 CN CN201620830907.5U patent/CN205862589U/en not_active Expired - Fee Related
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256636A (en) * | 2017-06-29 | 2017-10-17 | 段晓辉 | A kind of traffic flow acquisition methods for merging laser scanning and video technique |
| CN107505037A (en) * | 2017-07-05 | 2017-12-22 | 湖北鑫美企业发展股份有限公司 | A kind of supervising device that can finely identify vehicle |
| CN107505037B (en) * | 2017-07-05 | 2019-12-10 | 湖北鑫美企业发展股份有限公司 | Monitoring device capable of precisely identifying vehicle type |
| CN110470241A (en) * | 2019-08-19 | 2019-11-19 | 天津大学 | A kind of refractory brick curvature detection system and method based on structure light vision |
| CN110807936A (en) * | 2019-11-13 | 2020-02-18 | 佛山科学技术学院 | Statistical system for identifying vehicle model and measuring and calculating speed |
| CN112179307A (en) * | 2020-09-10 | 2021-01-05 | 上海交通大学 | Fuel cell metal bipolar plate forming error detection device |
| CN114202927A (en) * | 2021-12-27 | 2022-03-18 | 招商局重庆公路工程检测中心有限公司 | Vehicle type detection method based on multi-sensor fusion |
| CN114202927B (en) * | 2021-12-27 | 2022-11-15 | 招商局重庆公路工程检测中心有限公司 | Vehicle type detection method based on multi-sensor fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN205862589U (en) | A kind of automatic Vehicle Recognition System | |
| CN111583337B (en) | Omnibearing obstacle detection method based on multi-sensor fusion | |
| CN103902976B (en) | A kind of pedestrian detection method based on infrared image | |
| CN103500322B (en) | Automatic lane line identification method based on low latitude Aerial Images | |
| CN105313782B (en) | Vehicle travel assist system and its method | |
| CN104766058B (en) | A kind of method and apparatus for obtaining lane line | |
| Mu et al. | Traffic light detection and recognition for autonomous vehicles | |
| CN102567979B (en) | Vehicle-mounted infrared night vision system and multi-source images fusing method thereof | |
| CN104183127B (en) | Traffic surveillance video detection method and device | |
| CN104280036B (en) | A kind of detection of transport information and localization method, device and electronic equipment | |
| CN110163904A (en) | Object marking method, control method for movement, device, equipment and storage medium | |
| CN104021588B (en) | System and method for recovering three-dimensional true vehicle model in real time | |
| CN107463918A (en) | Lane line extracting method based on laser point cloud and image data fusion | |
| CN103473762B (en) | A kind of method for detecting lane lines and device | |
| CN107253485A (en) | Foreign matter invades detection method and foreign matter intrusion detection means | |
| CN204882391U (en) | Damaged automatic identification equipment in vehicular road surface based on image processing | |
| CN105067633A (en) | Vehicle-mounted type automatic pavement damage recognition device based on image processing and application method | |
| CN107085696A (en) | A kind of vehicle location and type identifier method based on bayonet socket image | |
| CN106575473A (en) | Method and axle-counting device for contact-free axle counting of a vehicle and axle-counting system for road traffic | |
| CN108154102A (en) | A kind of traffic sign recognition method | |
| CN107808123A (en) | The feasible area detecting method of image, electronic equipment, storage medium, detecting system | |
| CN106803262A (en) | The method that car speed is independently resolved using binocular vision | |
| Vestri et al. | Evaluation of a vision-based parking assistance system | |
| CN103729620A (en) | Multi-view pedestrian detection method based on multi-view Bayesian network | |
| CN107194343A (en) | Traffic lights detection method based on the related convolution in position with Fire models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170104 Termination date: 20170801 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |