CN107886728B - Video recognition device for truck model - Google Patents
Video recognition device for truck model Download PDFInfo
- Publication number
- CN107886728B CN107886728B CN201711201103.4A CN201711201103A CN107886728B CN 107886728 B CN107886728 B CN 107886728B CN 201711201103 A CN201711201103 A CN 201711201103A CN 107886728 B CN107886728 B CN 107886728B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- shooting camera
- induction coil
- license plate
- vehicle side
- 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
- 238000005303 weighing Methods 0.000 claims abstract description 22
- 230000006698 induction Effects 0.000 claims description 37
- 238000003860 storage Methods 0.000 claims description 6
- 238000005096 rolling process Methods 0.000 abstract description 9
- 238000012423 maintenance Methods 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 6
- 238000001228 spectrum Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
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
- G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
-
- 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
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- 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
- G08G1/042—Detecting movement of traffic to be counted or controlled using inductive or magnetic detectors
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of vehicle type identification of expressway intelligent charging management systems, in particular to a video identification device for a truck type; the video recognition device of the truck type comprises a ground sensing coil A, a ground sensing coil B, a license plate shooting camera, an embedded system with built-in image processing software, a vehicle side shooting camera, a weighing lane and a weighing platform, and is characterized in that the vehicle side shooting camera is arranged on a vertical rod at the other side of the weighing platform, the vehicle side shooting camera adopts a wide-angle lens, the vehicle side shooting camera is aligned to the center of the ground sensing coil A, the distance between the vehicle side shooting camera and the center of the ground sensing coil A is 18-22 meters, and the included angle between the vehicle side shooting camera and the driving direction of the lane is 45-135 degrees; the invention has the advantages that the vehicle type information is obtained by non-mechanical contact, the rolling of wheels is avoided, the measuring element is not damaged, the service life of the measuring element is long, and the measuring system does not need maintenance at ordinary times.
Description
Technical Field
The invention relates to the field of vehicle type identification of expressway intelligent charging management systems, in particular to a video identification device for a truck vehicle type.
Background
The highway load-carrying vehicle weighing and charging system needs to accurately judge the vehicle type of the load-carrying vehicle to obtain the axle weight and the total weight. At present, most of vehicle type recognition devices for load-carrying vehicles rely on wheel rolling, and the vehicle type is judged according to the number of times of wheel rolling. The vehicle rolling is an impact rolling process, and a rolled device is damaged due to excessive rolling times, so that the rolled device cannot work for a long time, the vehicle type recognition error is caused, and the long-time stable work of a charging system of a carrier vehicle is seriously influenced. How to solve the problem of excessive rolling times, the inventor refers to facial makeup software experience of face recognition and proposes a rolling-free technical scheme, namely shooting panoramic photos from the side of a load-carrying vehicle, analyzing the panoramic photo images to obtain facial makeup-vehicle spectrums of the load-carrying vehicle, and writing vehicle makeup recognition software. The computer or embedded system with built-in image processing software is used for recognizing the vehicle type by the vehicle spectrum, and the method is called as a video vehicle type recognition method for the truck for short. The method for identifying the truck type comprises the following steps: firstly, capturing a side panorama of a load-carrying vehicle from the side of the load-carrying vehicle to be tested; and then, identifying the characteristics of the load vehicle, and judging the vehicle type by using the vehicle spectrum software of the panoramic photograph of the side surface of the load vehicle, wherein the vehicle spectrum software comprises the axle number, single and double wheels, single axle, two axle groups, three axle groups, vehicle length and vehicle height. According to the technical scheme, the method comprises the steps of selecting cameras with different focal lengths according to weighing site conditions, and shooting panoramic pictures of the side surfaces of the load-carrying vehicles. The technical difficulties are two, namely, the length of the loading vehicle is very long and is more than 20 meters, and how to shoot a panoramic picture of the side surface of the vehicle; secondly, a vehicle model spectrum library and vehicle model identification software are established, and the vehicle model software is used for judging the vehicle model. Because the types of the truck are various, the truck has a whole truck with the load and a trailer with the load, the length of the truck is from a few meters to 21 meters, the heights of the truck are different, and the truck can be divided into 2-6 axles according to the axle number, and 22 types of truck types are all used. The technical scheme is as follows: two cameras, the vehicle front camera shoots the license plate, and the vehicle side camera shoots the vehicle side panoramic photo. The camera is characterized in that the long-focus camera can shoot more distant objects, and the short-focus camera can shoot more wide objects. A common 135/120 camera has a lens focal length of 58/75 mm, and belongs to a middle-focus camera. A common 135/120 camera is used for photographing a load-carrying vehicle with the length of 20 meters, and the photographing distance is far. An ideal target is that the side face of a 50-meter external vehicle is photographed vertically, the length of the vehicle, whether the length of the vehicle is interrupted (trailer), the height of the vehicle, the number of axles and axle groups (single, double or triple axle) are measured, and the vehicle type is judged according to parameters; shooting the side face of a vertical vehicle, wherein the distance between the side face of a measuring lane and the side face of the measuring lane is required to have a 50-meter open area, a space area or not allowed; the included angle is 60 degrees, and the side distance is 40 meters; the included angle is 30 degrees, and the side distance becomes 25 meters. From this calculation, shooting with a normal camera is difficult. The wide-angle camera (the lens of the camera adopts a wide-angle lens), the focal length of the wide-angle lens is 28 mm, the included angle of 90/60/30 degrees is selected, the shooting distance is shortened to 20 meters/16 meters/10 meters, and the shooting distance can be closer after the camera has the included angle. And finally, restoring the snap-shot vehicle side image by using software, taking the middle vertical line of the image as a central line, processing two sides of the vehicle image, scaling up the image on one side, scaling down the image on the other side, and recovering the effect of shooting the vehicle side at a vertical angle and bilateral symmetry pictures. And then using spectrum recognition software to measure the length of the vehicle, whether the length of the vehicle is interrupted (trailer), the height of the vehicle, the number of axles, axle groups (single, double or triple shaft), single and double wheels, and judging the vehicle type according to the parameters.
Disclosure of Invention
According to the technical scheme of the invention, a wide-angle camera takes a panoramic picture image of the side face of a vehicle to identify, and a truck model video identification device comprises a ground induction coil A, a ground induction coil B, a license plate shooting camera, an embedded system with built-in image processing software, a vehicle side face shooting camera, a weighing lane and a weighing platform, and is characterized in that the ground induction coil A and the ground induction coil B are arranged below the pavement of the weighing lane in front of the weighing platform, the ground induction coil A is arranged in front of the ground induction coil A, the ground induction coil B is arranged behind the ground induction coil A, and the distance between the ground induction coil A and the ground induction coil B is selected to be 4-6 meters; the license plate shooting camera is arranged on the upright post at one side of the weighing platform, and is aligned with the ground induction coil B; the other side of the weighing platform is provided with a cabinet of an embedded system with built-in image processing software and a vehicle side shooting camera, wherein the height of the upright is 3 meters, the vehicle side shooting camera is arranged on the upright, the vehicle side shooting camera adopts a wide-angle lens, the vehicle side shooting camera is aligned to a ground induction coil A, the distance between the vehicle side shooting camera and the ground induction coil A is 18-22 meters, and the included angle between the vehicle side shooting camera and the driving direction of a lane is 45-135 degrees; the preferable included angle between the vehicle side shooting camera and the driving direction of the lane comprises 45-80 degrees and 100-135 degrees.
The video recognition device for the truck model is characterized in that a ground induction coil B of a ground induction coil A is electrically connected with an embedded system with built-in image processing software, a license plate shooting camera and a vehicle side shooting camera are electrically connected with the embedded system with built-in image processing software through network cables, and a serial port of the embedded system with built-in image processing software is electrically connected with an upper computer.
The video recognition device for the truck type is characterized in that an embedded system with built-in image processing software receives license plate image information of a license plate shooting camera, and the license plate image information is obtained after processing and is stored in a storage unit taking the license plate information as a title; after receiving a vehicle side image of a vehicle side shooting camera, an embedded system with built-in image processing software balances the image left and right by taking a central vertical line of the vehicle side image as a central line, and enlarges the left side and reduces the right side or vice versa; taking the left and right balanced vehicle side images as the basis, and measuring single and double wheel information of the vehicle by using image vehicle software; measuring vehicle axle information and axle set information with wheel information; measuring the length of the vehicle; judging the type of the vehicle according to the information; writing the vehicle type information of the vehicle into a storage unit taking the license plate information as a title; and taking the license plate information as a title, and uploading the license plate information to an upper computer license plate and vehicle type information.
The working principle of the video recognition device for the truck type is described as follows: and (3) circuit triggering: the truck enters a weighing lane, the truck firstly presses a ground induction coil A, and a license plate camera and a vehicle side shooting camera enter a shooting state; the lorry is further pressed to the ground induction coil A and the ground induction coil B at the same time, the license plate camera captures the license plate of the lorry for several times, and an embedded system with built-in image processing software is uploaded; meanwhile, the side face of the vehicle shoots a camera for several times to shoot a side panoramic photo of the truck, and the embedded system with built-in image processing software is uploaded. An embedded system with built-in image processing software receives license plate image information of a license plate shooting camera, obtains license plate information after processing, and stores the license plate information by taking a license plate as a title; after receiving a vehicle side image of a vehicle side shooting camera, an embedded system with built-in image processing software balances the image left and right by taking a central vertical line of the vehicle side image as a central line, and enlarges the left side and reduces the right side or vice versa; taking the left and right balanced vehicle side images as the basis, and measuring single and double wheel information of the vehicle; measuring vehicle axle information and axle set information according to the wheel information, and judging the vehicle type of the vehicle according to the vehicle length; the vehicle type information of the vehicle is written into the license plate information storage unit, and the license plate information is taken as the license plate information to be uploaded to the upper computer.
The video recognition device for the truck model has the advantages that the non-mechanical contact is used for obtaining the information of the truck model, no wheel rolling device is arranged, the measuring element has no damage, the service life of the measuring element is long, and the measuring system does not need maintenance at ordinary times.
Drawings
FIG. 1 is a schematic diagram of the distribution of components of a truck model video recognition device installed on site;
FIG. 2 is a circuit assembly connection diagram of a truck model video recognition device;
Wherein: 1. the system comprises a truck, a ground induction coil A, a ground induction coil B, a license plate shooting camera, an embedded system with built-in image processing software, a vehicle side shooting camera, a weighing lane, a weighing platform and an upper computer.
Detailed Description
The specific embodiment is described with reference to a video recognition device of a truck model installed at an entrance of a highway weighing lane in the city of fortune, which comprises the following steps:
Presetting working conditions of a shooting camera:
Working power supply: 12VDC (maximum current 3A, quiescent current 0.1A).
Operating temperature: -30-85 ℃.
Working humidity: 30-90% (relative humidity).
Snapshot time: and most rapidly about 1-50 milliseconds.
The embedded system with built-in image processing software adopts STM32F103VCT6, and preset startup self-checking.
The working process of the video recognition device for the truck type comprises the following steps: the method comprises the steps that a truck enters a weighing lane entrance, a vehicle is pressed to a ground induction coil A, then is simultaneously pressed to the ground induction coil A and the ground induction coil B, a license plate camera captures the license plate of the truck for several times, and an embedded system with built-in image processing software is uploaded; meanwhile, the side face of the vehicle shoots a camera for several times to shoot a side panoramic photo of the truck, and the embedded system with built-in image processing software is uploaded. An embedded system with built-in image processing software receives license plate image information of a license plate shooting camera, obtains license plate information after processing, and stores the license plate information; after receiving a vehicle side image of a vehicle side shooting camera, an embedded system with built-in image processing software balances the image left and right by taking a central vertical line of the vehicle side image as a central line, and enlarges the left side and reduces the right side or vice versa; taking the left and right balanced vehicle side images as the basis, measuring single and double wheel information of the vehicle, and measuring axle information, axle group information and vehicle length of the vehicle by using wheel information, and judging the vehicle type of the vehicle; the vehicle type information of the vehicle is written into the license plate information storage unit, and the license plate information is taken as the license plate information to be uploaded to the upper computer. In the practical test, when the included angle between the vehicle side shooting camera and the driving direction of the lane is 90 degrees, the single-wheel and double-wheel information of the vehicle cannot be obtained through the analysis processing of the vertical shooting photo, so that an 80-100-degree interval around 90 degrees is specially avoided; therefore, the preferable included angle between the vehicle side shooting camera and the driving direction of the lane comprises 45-80 degrees and 100-135 degrees.
The video recognition device for the truck model has the advantages that the non-mechanical contact is used for obtaining the information of the truck model, no wheel rolling device is arranged, the measuring element has no damage, the service life of the measuring element is long, and the measuring system does not need maintenance at ordinary times.
Claims (1)
1. The video recognition device of the truck type comprises a ground induction coil A, a ground induction coil B, a license plate shooting camera, an embedded system with built-in image processing software, a vehicle side shooting camera, a weighing lane and a weighing platform, and is characterized in that the ground induction coil A and the ground induction coil B are arranged below the road surface of the weighing lane in front of the weighing platform, the ground induction coil A is arranged in front of the ground induction coil B, the ground induction coil B is arranged behind the ground induction coil A, and the distance between the ground induction coil A and the ground induction coil B is selected to be 4-6 meters; the license plate shooting camera is arranged on the upright post at one side of the weighing platform, and is aligned with the ground induction coil B; the other side of the weighing platform is provided with a cabinet of an embedded system with built-in image processing software and a vehicle side shooting camera, wherein the height of the upright is 3 meters, the vehicle side shooting camera is arranged on the upright, the vehicle side shooting camera adopts a wide-angle lens, the vehicle side shooting camera is aligned to a ground induction coil A, the distance between the vehicle side shooting camera and the ground induction coil A is 18-22 meters, and the included angle between the vehicle side shooting camera and the driving direction of a lane is 45-80 degrees and 100-135 degrees;
the ground induction coil A is electrically connected with an embedded system with built-in image processing software, the license plate shooting camera and the vehicle side shooting camera are electrically connected with the embedded system with built-in image processing software through network cables, and a serial port of the embedded system with built-in image processing software is electrically connected with an upper computer;
An embedded system with built-in image processing software receives license plate image information of a license plate shooting camera, obtains license plate information after processing, and stores the license plate information in a storage unit taking the license plate information as a title; after receiving a vehicle side image of a vehicle side shooting camera, an embedded system with built-in image processing software balances the image left and right by taking a central vertical line of the vehicle side image as a central line, and enlarges the left side and reduces the right side or vice versa; taking the left and right balanced vehicle side images as the basis, and measuring single and double wheel information of the vehicle by using image vehicle software; measuring vehicle axle information and axle set information with wheel information; measuring the length of the vehicle; judging the type of the vehicle according to the information; writing the vehicle type information of the vehicle into a storage unit taking the license plate information as a title; and taking the license plate information as a title, and uploading the license plate information to an upper computer license plate and vehicle type information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711201103.4A CN107886728B (en) | 2017-11-27 | 2017-11-27 | Video recognition device for truck model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711201103.4A CN107886728B (en) | 2017-11-27 | 2017-11-27 | Video recognition device for truck model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107886728A CN107886728A (en) | 2018-04-06 |
| CN107886728B true CN107886728B (en) | 2024-05-10 |
Family
ID=61775360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711201103.4A Active CN107886728B (en) | 2017-11-27 | 2017-11-27 | Video recognition device for truck model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107886728B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109583394B (en) * | 2018-12-05 | 2024-01-12 | 陕西四维衡器科技有限公司 | Method and special equipment for identifying number of vehicle tires in expressway toll collection system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0382493U (en) * | 1989-12-07 | 1991-08-22 | ||
| JPH08233525A (en) * | 1995-02-24 | 1996-09-13 | Hitachi Ltd | Vehicle-type discriminating apparatus |
| JPH0954891A (en) * | 1995-08-15 | 1997-02-25 | Babcock Hitachi Kk | Method for discriminating vehicle type by image processing and device therefor |
| US5809658A (en) * | 1993-09-29 | 1998-09-22 | Snap-On Technologies, Inc. | Method and apparatus for calibrating cameras used in the alignment of motor vehicle wheels |
| JP2008310622A (en) * | 2007-06-15 | 2008-12-25 | Mitsubishi Heavy Ind Ltd | Vehicle number recognition apparatus and vehicle number recognition method |
| JP2009140381A (en) * | 2007-12-10 | 2009-06-25 | Toshiba Corp | Toll collection system and method |
| CN103794056A (en) * | 2014-03-06 | 2014-05-14 | 北京卓视智通科技有限责任公司 | Vehicle type accurate classification system and method based on real-time double-line video stream |
| CN204632107U (en) * | 2015-05-21 | 2015-09-09 | 武汉万集信息技术有限公司 | A kind of combined model recognition system based on scanning type laser stadimeter |
| CN204808588U (en) * | 2015-07-29 | 2015-11-25 | 王云 | Vehicle type identification system |
| CN105719354A (en) * | 2016-01-15 | 2016-06-29 | 成都宜泊信息科技有限公司 | Trailer-type vehicle identification and parking charging system and method |
-
2017
- 2017-11-27 CN CN201711201103.4A patent/CN107886728B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0382493U (en) * | 1989-12-07 | 1991-08-22 | ||
| US5809658A (en) * | 1993-09-29 | 1998-09-22 | Snap-On Technologies, Inc. | Method and apparatus for calibrating cameras used in the alignment of motor vehicle wheels |
| JPH08233525A (en) * | 1995-02-24 | 1996-09-13 | Hitachi Ltd | Vehicle-type discriminating apparatus |
| JPH0954891A (en) * | 1995-08-15 | 1997-02-25 | Babcock Hitachi Kk | Method for discriminating vehicle type by image processing and device therefor |
| JP2008310622A (en) * | 2007-06-15 | 2008-12-25 | Mitsubishi Heavy Ind Ltd | Vehicle number recognition apparatus and vehicle number recognition method |
| JP2009140381A (en) * | 2007-12-10 | 2009-06-25 | Toshiba Corp | Toll collection system and method |
| CN103794056A (en) * | 2014-03-06 | 2014-05-14 | 北京卓视智通科技有限责任公司 | Vehicle type accurate classification system and method based on real-time double-line video stream |
| CN204632107U (en) * | 2015-05-21 | 2015-09-09 | 武汉万集信息技术有限公司 | A kind of combined model recognition system based on scanning type laser stadimeter |
| CN204808588U (en) * | 2015-07-29 | 2015-11-25 | 王云 | Vehicle type identification system |
| CN105719354A (en) * | 2016-01-15 | 2016-06-29 | 成都宜泊信息科技有限公司 | Trailer-type vehicle identification and parking charging system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107886728A (en) | 2018-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111932693B (en) | Urban road side parking lot management system | |
| CN110533923B (en) | Parking management method and device, computer equipment and storage medium | |
| CN111739335B (en) | Parking detection method and device based on visual difference | |
| CN111325858B (en) | Method for realizing automatic charging management aiming at roadside temporary parking space | |
| CN105721764B (en) | Vehicle-mounted pattern recognition device and its manufacturing method | |
| CN206411865U (en) | Vehicle overload overload supervisory systems | |
| CN108133599A (en) | A kind of slag-soil truck video frequency identifying method and system | |
| CN111613088A (en) | Parking charging management system and method | |
| CN113744420B (en) | Road parking charge management method, system and computer readable storage medium | |
| KR20230009520A (en) | Real-time Port Hall Detection Device Using Police Cars | |
| CN113850137A (en) | Power transmission line image online monitoring method, system and equipment | |
| CN111192462A (en) | Overrun information acquisition method, device and system and overrun detection equipment | |
| CN112329747A (en) | Vehicle parameter detection method based on video identification and deep learning and related device | |
| CN107886728B (en) | Video recognition device for truck model | |
| CN108292469A (en) | Method of determining position information, location information determining device and, location information determines program | |
| CN112750216A (en) | Novel parking space detection video pile and detection system thereof | |
| KR101530851B1 (en) | Monitoring method of vehicle black box camera and vehicle black box camera implementing thereof | |
| TW201729165A (en) | Method for billing of a parking fee particularly to a method for billing of a parking fee for parking at a parking space | |
| CN214010505U (en) | Unattended intelligent wagon balance capable of improving license plate recognition rate | |
| CN108765964A (en) | A kind of automotive type video identification device and method | |
| CN112348004B (en) | Gas station license plate unmanned aerial vehicle recognition system and method based on Internet of things | |
| CN201869279U (en) | Intelligent high definition special-purpose traffic detection capturing camera | |
| CN210491012U (en) | Vehicle license plate photographing system | |
| CN108538053A (en) | A kind of automatic detection vehicle transfinites system | |
| CN112927556A (en) | Monitoring system for high-order video curb parking |
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 |