CN103413439B - A kind of passenger vehicle based on video and lorry sorting technique - Google Patents
A kind of passenger vehicle based on video and lorry sorting technique Download PDFInfo
- Publication number
- CN103413439B CN103413439B CN201310326455.8A CN201310326455A CN103413439B CN 103413439 B CN103413439 B CN 103413439B CN 201310326455 A CN201310326455 A CN 201310326455A CN 103413439 B CN103413439 B CN 103413439B
- Authority
- CN
- China
- Prior art keywords
- video
- vehicle
- image
- lorry
- camera
- 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
The present invention gives a kind of passenger vehicle based on video and lorry sorting technique, the method is auxiliary with LED, utilize the principle of the mirror-reflection of glass for vehicle window, according to lorry this distinguishing feature different from Bus window number, pass through vehicle tracking, binary conversion treatment, Band object detects scheduling algorithm, obtain the reflected image of target LED in video sequence, realize the detection identification to whether there is glass for vehicle window, and judge whether abundant glass for vehicle window, carry out in real time with this to large and medium bus and lorry kind, reliable division, this technology adopts contactless mode to detect, failure rate is low, passenger vehicle and car need not arrange special passage, greatly improve the utilization factor of the finite space, can not traffic be blocked when installing and keep in repair, have broad application prospects in highway tolling system.
Description
Technical field
The invention belongs to video to detect and technical field of information processing, be specifically related to a kind of based on the lorry of video and the sorting technique of passenger vehicle.
Background technology
In the highway tolling system of China, be different to the expenses standard system of lorry and passenger vehicle, wherein, its pay load of charge Main Basis of lorry, the charge of passenger vehicle then Main Basis vehicle kind or appraise and decide passengers quantity.Therefore, in Fare Collection System, must first distinguish lorry and passenger vehicle.
At present, the Expressway Toll Methods of China mainly contains semi automatic toll and ETC(non-parking charge) two kinds.In semi automatic toll mode, main by artificial differentiation lorry and passenger vehicle; And in ETC, in order to distinguish lorry and passenger vehicle, general employing arranges special passenger vehicle and lorry passage, to realize lorry and the object of charging distinguished by passenger vehicle.
No matter be semi automatic toll or ETC, if the automatic identification of lorry and passenger vehicle can be realized, greatly will improve charge efficiency and management level.Such as, the lane in which the drivers should pay fees that some flow is little can realize unattended self-service charge, lorry and passenger vehicle also can arrange separately special toll collection lanes, so not only use manpower and material resources sparingly, make full use of path resource, and be convenient to unified management, Fare Collection System is improved more with efficient.As can be seen here, the automatic identification technology of research passenger vehicle and lorry, is of great practical significance for the automatization level improving highway tolling system.
Current vehicle classification technology mainly contains pressure transducer sorting technique, laser detection sorting technique, infrared detection sorting technique, electromagnetic induction coil sorting technique, wireless telecommunications sorting technique etc., system and the specific classification standard of these methods are closely related, and thus system portability is poor; Adopt the system of pressure transducer or electromagnetic induction coil also to need road surface pavement again, inconvenience is installed, lacks dirigibility.These systems also have a common shortcoming, and be exactly because equipment work under bad environment, serviceable life are limited, the vehicle identification system based on wireless communication technique needs all vehicles to install impulse sender, invests very large.
Summary of the invention
For the present situation of highway tolling system, the object of the invention is to, propose a kind of method that passenger vehicle based on video and lorry are classified, the method can realize classifying in real time, reliably to the big-and-middle-sized lorry in range of video and passenger vehicle.
In order to realize above-mentioned technical assignment, the technical solution used in the present invention is:
A kind of passenger vehicle based on video and lorry sorting technique, the method utilizes the sequence of video images of computing machine to camera acquisition to process the classification realizing passenger vehicle and lorry, described computing machine is connected with infrared vehicle separation vessel, infrared vehicle separation vessel is arranged on freeway toll station feeder connection place, near the side in charge station direction, LED is installed at infrared vehicle separation vessel, vertical setting, first video camera is installed bottom LED, side in the middle part of LED is provided with the second video camera, the camera lens of the first video camera and the second video camera is all parallel to road surface, and it is vertical with road direction, the first described video camera is connected with computing machine respectively by an image pick-up card with the second video camera, should comprise the following steps based on the passenger vehicle of video and lorry sorting technique:
Step one, first video camera and the second cameras capture video information within the vision, computing machine carries out image acquisition to the video information of the first video camera and the second camera acquisition respectively by image pick-up card, obtains the sequence of video images of the first video camera and the second camera acquisition;
Step 2, whether infrared vehicle separation vessel monitoring road has vehicle process, if the headstock process of vehicle detected, then this information is passed to computing machine, and note video frame number is N, and video adds up to M, and the initial value of M and N is 0; Perform step 3;
Step 3, computing machine utilizes the sequence of video images of the target tracking algorism of feature based angle point to the first camera acquisition to process:
(1) the first camera acquisition to sequence of video images in, selecting video image sequence current frame image, adopts Moravec algorithm to extract Corner, and centered by this angle point, chooses an image block as template;
(2) employing is followed the tracks of based on Block Matching Algorithm, in the next frame image of present frame, the pixel value of block onesize with above-mentioned template correspondence position and the pixel value of template are done difference, if the number that margin of image element is not 0 is greater than 5, then perform step 4, otherwise return step 3 continuation execution;
Step 4, computing machine to the second camera acquisition to sequence of video images process:
(1) demarcation of target area
The second camera acquisition to sequence of video images in, computer selecting current frame image, is divided into the identical region of three sizes by current frame image with vertical direction, chooses middle region as processing region;
(2) background subtraction is adopted processing region to be carried out to the segmentation of target
Adopt global threshold binarization method to process to each pixel of the processing region chosen, then the Region dividing after process is become the block that multiple size is identical, then carry out block-based binary conversion treatment to each piece;
(3) connected component labeling
Adopt eight neighborhood labeling algorithm to carry out connected component labeling to the image block after binary conversion treatment, and carry out the removal of connected domain and fill merging and obtain Contiguous graphics; Again Contiguous graphics is carried out to the closed operation process in morphologic filtering, obtain destination object;
(4) detection of Band object
The geometric characteristic of evaluating objects object, calculates the aspect ratio of destination object, according to ratio, if the aspect ratio of destination object is greater than 25, then determines that this target is Band object;
(5) the tracking statistics of Band object
If destination object is not Band object, then video sum adds 1; If destination object is Band object, then video frame number N adds 1, and video sum adds 1; If infrared vehicle separation vessel detects that vehicle tail is by infrared vehicle separation vessel, then perform step 5, otherwise return step 3;
Step 5, computing machine stops the process to the sequence of video images that the first video camera and the second camera acquisition arrive, now ratio calculated k=N/M; If k > 50%, then judge that the vehicle of firm process is as passenger vehicle, otherwise be lorry.
Further, the length of described LED is 1.5 ~ 2m, and width is 0.015m, and the height on the distance ground, bottom of LED is 1.2 ~ 2m, and the light intensity of LED is 2500 ~ 3000cd.
Further, after adopting Moravec algorithm to extract Corner in step 3, centered by this angle point, a size is chosen for the image block of 25*25 pixel is as template.
The present invention is lorry based on video and passenger vehicle sorting technique, is a kind of novel video detection technology, can accurately classifies to the large and medium bus in range of video and lorry, and not by environmental restraint, real-time is good, and be easy to realize, accuracy is higher.Compared with prior art, this technology adopts contactless mode to detect, failure rate is low; Passenger vehicle and car need not arrange special passage, greatly improve the utilization factor of the finite space; Can not traffic be blocked when installing and keep in repair, have broad application prospects in highway tolling system.
Accompanying drawing explanation
Fig. 1 is the artwork of equipment in the present invention;
Fig. 2 is overall flow figure of the present invention;
Fig. 3 is mirror-reflection schematic diagram;
Fig. 4 is the schematic diagram utilizing Moravec algorithm to extract an angle point on image;
Fig. 5 (a) is the image of the LED of the Bus window reflection of the second camera acquisition;
Fig. 5 (b) is the image of the truck body reflection LED of the second camera acquisition;
Fig. 6 (c) adopts the result of global threshold binarization method process for Fig. 5 (a);
Fig. 6 (d) adopts the result of global threshold binarization method process for Fig. 5 (b);
Fig. 7 (e) is the image after the block-based binaryzation of Fig. 5 (a), connected component labeling;
Fig. 7 (f) is the image after the block-based binaryzation of Fig. 5 (b), connected component labeling;
Fig. 8 is the schematic diagram of simulation tracing statistics Band object;
Below in conjunction with drawings and Examples, the present invention is described in further detail.
Embodiment
The present embodiment provides a kind of method that passenger vehicle based on video and lorry are classified, and whether there is abundant vehicle window, distinguishing passenger vehicle and lorry with this mainly through detecting car body.Specific implementation is auxiliary with LED, utilize the principle of the mirror-reflection of glass for vehicle window, according to lorry this distinguishing feature different from Bus window number, by analyzing the reflected image of target LED in video sequence, to realize the detection identification to whether there is glass for vehicle window, and judging whether abundant glass for vehicle window, carrying out in real time with this to passenger vehicle and lorry kind, reliable division, as shown in Figure 1 to Figure 3; Specifically follow these steps to carry out:
The selection of equipment:
Before carrying out equipment installation, first to the length of existing passenger vehicle and lorry with highly carry out statistical study, so that suitable selected equipment and carry out the installation of equipment.In table 1 and table 2:
The existing lorry specification of table 1
The existing passenger vehicle specification of table 2
Note: " vehicle window overall length " in table 1 and table 2 refers to the length sum (do not comprise the length of vehicle window intermediate spacing section) of all vehicle windows of a side of vehicle along direction of traffic
Learnt by large quantitative statistics, the height of existing passenger vehicle and lorry is between 1.8 meters to 3.7 meters, the height of glass for vehicle window is between 0.5 meter to 1.5 meters, therefore the length of LED is between 1.5 meters to 2 meters, the image of light bar just clearly can be reflexed in such glass for vehicle window, in order to reduce the impact of surrounding enviroment on system, light bar brightness range of choice is 2500 ~ 3000 candelas.
This system coordinates the existing facility of Current Highway charge station to use, at freeway toll station feeder connection, echelette vehicle separator is installed, near the side in charge station direction, described LED is installed at infrared vehicle separation vessel, distance 1.2 meters, road surface, LED bottom is high to 2 meters, vertical installation, the first video camera is arranged on LED bottom, and camera lens is parallel to level road, vertical with road direction, catch the car body through vehicle; Road direction, is the direction of vehicle movement; Install the second video camera in the side in light bar centre position, camera lens is parallel to horizontal direction, vertical with road direction, through the vehicle window image of vehicle on capture channel; Then carry out collection image by image pick-up card, the image collected passed to master-control room computing machine and carries out follow-up process, the first video camera and the second video camera with the use of, as shown in Figure 2.
The image major body image of the first camera acquisition, for judging whether vehicle is when by infrared vehicle separation vessel, have the situation of stopping, and the second cameras capture is the frame number of image of the LED of vehicle window reflection, and the totalframes of entire vehicle by gathering during the second video camera, by have the frame number of LED reflected image and entire vehicle by time the ratio of totalframes, can judge that what vehicle the vehicle passed through is, therefore, when vehicle is when stopping by vehicle separator, if the image processing process of computing machine to the second camera acquisition continues to carry out, the frame number of LED reflected image is then had not increase, but the video totalframes that the second camera acquisition arrives is increasing always, the inaccurate of result can be caused.Therefore computing machine starts the prerequisite of the image procossing of the second camera acquisition is that vehicle is kept in motion, and this computer-chronograph just can add up the totalframes that the frame number that comprises LED reflected image and entire vehicle pass through.
Step one, first video camera and the second cameras capture video information within the vision, computing machine carries out image acquisition to the video information of the first video camera and the second camera acquisition respectively by image pick-up card, obtains the sequence of video images of the first video camera and the second camera acquisition;
Step 2, infrared vehicle separation vessel monitoring road on whether have vehicle process, if the headstock process of vehicle detected, then this information is passed to computing machine, computing machine start to camera acquisition to image information process.Note video frame number is N, and video adds up to M, and the initial value of M and N is 0; Perform step 3;
Step 3, computing machine utilizes the sequence of video images of the target tracking algorism of feature based angle point to the first camera acquisition to process, and realizes the tracking of vehicle, to guarantee that vehicle is kept in motion, if vehicle is not in motion state, so do not perform step 4;
(1) classical Moravec algorithm is adopted to extract angle point, Moravec algorithm utilizes the variance of gray scale to extract angle point, this algorithm is by definition " interest value ", carry out closed operation process and non-maximal value on this basis to suppress to calculate angle point, the angle point obtained as shown in Fig. 4 (point in image centre circle), being implemented as follows of Morave algorithm:
With pixel (x a certain on image, y) centered by, set up the window (window of such as 5*5) that a size is n*n, as shown in Figure 4, when window moves along transverse direction, longitudinal direction and two cornerwise directions, calculate interest value (quadratic sum of neighbor gray scale difference) g on four direction respectively
1, g
2, g
3, g
4, expression formula is as follows:
In formula, k=INT (n/2) (round n/2, n is window width); g
1represent horizontal interest value, g
2represent longitudinal interest value, g
3and g
4represent two diagonal interest value, i is the number of pixels of movement, and k is the ultimate range of movement.From g
1, g
2, g
3, g
4middle selected value minimum value is as the metric of this interest value.First the interest value of point each on image is selected, in all these interest value, then select the point being greater than a certain threshold value as angle point.
The direction gradient difference of this pixel of the larger explanation of interest value is larger, and the quality of angle point is better.Interest value is greater than threshold value T(T desirable 120 ~ 130) point screen as angle point, centered by this point, choose the block that a size is 25*25 as template.
(2) employing is followed the tracks of based on Block Matching Algorithm, the method of Block-matching is as follows: be located in current frame image, an angle point P (x is detected with Moravec algorithm, y), then in the next frame image of present frame, by the pixel value of the block onesize with above-mentioned template correspondence position and the pixel value of template poor, margin of image element be not 0 number p be greater than 5, if (two two field pictures there are differences, the comparison of pixel value can be compared by a certain size block in selected digital image, find through test of many times, the block of selected 25*25 pixel compares, the number of pixel change is less than 5 ~ 10, then think that this two two field picture not there are differences, here 5 are selected) then perform step 4, otherwise continue to perform step 3.
Adopt and follow the tracks of based on Block Matching Algorithm, so when vehicle stops in the process by infrared vehicle separation vessel, angle point on angle point on present image and next frame image does not change, then computing machine does not start the work for the treatment of of the image that the second camera acquisition arrives; If vehicle does not remain static, so present frame is different with the corner location information of next frame, the number p that reaction is margin of image element position 0 on margin of image element is greater than 5, now namely judges state of motion of vehicle, then computing machine start to the second camera acquisition to image process.
Step 4, computing machine to the second camera acquisition to sequence of video images process:
Carry out the Band object statistics of LED reflected image, be implemented as follows:
(1) demarcation of target area.
In the sequence of video images of the second camera acquisition, spotting surveyed area, in order to improve the speed of image procossing, current frame image is divided into the identical region of three sizes with vertical direction, the region choosing in the middle of whole two field picture 1/3rd processes, as shown in Figure 5, (a) for collect Bus window reflection LED image, LED is obvious; B LED image that () reflects for truck body, vehicle body reflection is not obvious;
(2) background subtraction is adopted to carry out the segmentation of target
Utilize the background image obtained (when vehicle does not arrive, the image of the current location of the second camera acquisition) B (x, y) with present frame target area image f (x, y) poor, then make comparisons with the threshold value of setting, thus obtain target information D (x, y), as shown in the formula:
Wherein T
2(between 150 to 180) are the threshold value of setting, in image, D (x, y)=255(0 represents black, and 255 represent white) pixel representative be object pixel, the result of each employing global threshold binarization method process namely on image, as shown in Figure 6.On this basis image is divided into the block of multiple number size; The pixel size of this video sequence is the block that 720*288 can be divided into that size is 8*6, the number of white pixel in adding up each piece, if be greater than 1/3rd of number of pixels sum in this block, just all make pixel values all in this block into 255, then complete block-based binary conversion treatment;
(3) mark of connected domain
Connectedness between image pixel determines the key concept of object boundary information and area information in image.Whether two pixels connect needs confirms whether they contact in some sense.Adopt eight neighborhood labeling algorithm to carry out connected component labeling to the image block after binary conversion treatment, eight neighborhood labeling algorithm is specific as follows:
If some set { (x+p, y+q) corresponding with pixel (x, y); , p and q is a pair significant integer, is referred to as the neighborhood of pixel (x, y).First 8 neighborhoods of pixel (x, y) are defined, as follows:
F8(x,y)＝{f(x-1,y-1),f(x-1,y),f(x-1,y+1),f(x,y-1),
f(x,y+1),f(x+1,y+1),f(x+1,y),f(x+1,y+1)}
If have pixel f (x, y) and f (x+p, y+q) in same width image-region, be communicated with if f (x, y) and f (x+p, y+q) exists 8 vertex neighborhoods, f (x, y) and f (x+p, y+q) is then claimed to be communicated with.The object of connected domain research is not pixel but image block, if two image blocks meet 8 Neighbor Conditions and just think that the two is connected, be labeled as same target, again the target after mark is removed, fills, merged and obtain Contiguous graphics, then Contiguous graphics is carried out to the closed operation process in morphologic filtering, obtain destination object.
(4) Band object detects
Analyze treated after obtain destination object, calculate the aspect ratio of destination object, width due to LED is 15mm, the height of the image that light bar becomes in glass for vehicle window is more than or equal to 1/2nd of vehicle window height, if 1/2nd of vehicle window height and light bar width ratio range between 25 to 40, so when the aspect ratio of object block is greater than 25, then think that this target is Band object, the i.e. result of LED after reflected image process formed by glass for vehicle window, as shown in (e) in Fig. 7; F therefore () result owing to being vehicle body reflection LED image procossing is not Band object after the process of LED reflectogram.
(5) the tracking statistics of Band object
If destination object is not Band object, then video sum adds 1; If destination object is Band object, then video frame number N adds 1, and video sum adds 1; If now infrared vehicle separation vessel detects that vehicle tail passes through, so perform step 5, otherwise return step 3; Here video counts N i.e. the second camera acquisition to vehicle on the frame number of vehicle window, video adds up to totalframes when vehicle crosses from the beginning to the end.
Step 5, computing machine stops the process to the sequence of video images that the first video camera and the second camera acquisition arrive, now ratio calculated k=N/M; If k > 50%, then judge that the vehicle of firm process is as passenger vehicle, otherwise be lorry.
M and the N value ratio calculated k utilizing step 4 to obtain, k=N/M.According to the Vehicle length of statistics in table 1 and table 2, analyze, the ratio of Bus window length and vehicle commander is greater than 90%, and the ratio of lorry vehicle window length and vehicle commander is less than 20%, and therefore when k is greater than 50%, this car is passenger vehicle, otherwise is lorry.As everyone knows, the glass for vehicle window number of passenger vehicle and lorry is different, and passenger vehicle has glass to exist from headstock to the tailstock, and lorry only has headstock to have glass, gets up also relatively more directly perceived, easily according to the glass for vehicle window identification of car body.Therefore, glass for vehicle window can be utilized to carry out the Accurate classification of passenger vehicle and lorry.
Fig. 8 is simulation tracing statistics Band object process, and in whole process, LED is static, and car body is motion, now supposes that car body is static, is so just equivalent to LED in motion, scans vehicle window.When a car by time, totalframes when adding up total number of image frames and have the appearance of glass for vehicle window, so just can calculate the number percent that glass for vehicle window total length accounts for whole length over ends of body, finally carry out the classification of passenger vehicle and lorry.
It is below the specific embodiment that inventor provides.
Embodiment:
Installing model at freeway toll station feeder connection is MYL infrared vehicle separation vessel, install in this position that a length is 2 meters, width is that (model is: soft light bar 220V60*5050 for the LED of 15 millimeters, white,) light bar bottom distance 1.2 meters, road surface high, first video camera is arranged on LED bottom, the specification that the side in LED centre position arranges the second video camera first video camera and the second video camera is that model is: gunlock, sharpness: 460 lines, lens focus: 8MM, monitoring camera lens: standard, photosensitive area: 1/3 cun.
In the video sequence known, when have a lorry by time, the N value of statistics is 15, M value is 122, and calculating gained k value is 12%, thus can judge that it is lorry, as shown in Fig. 5 (a), conforms to actual.When have a passenger vehicle by time, the N value of statistics is 63, M value is 57, and calculating gained k value is 90%, thus can judge that it is passenger vehicle, as shown in Fig. 5 (b), conforms to actual.
Claims (3)
1. the passenger vehicle based on video and lorry sorting technique, the method utilizes the sequence of video images of computing machine to camera acquisition to process the classification realizing passenger vehicle and lorry, it is characterized in that, described computing machine is connected with infrared vehicle separation vessel, infrared vehicle separation vessel is arranged on freeway toll station feeder connection place, near the side in charge station direction, LED is installed at infrared vehicle separation vessel, vertical setting, first video camera is installed bottom LED, side in the middle part of LED is provided with the second video camera, the camera lens of the first video camera and the second video camera is all parallel to road surface, and it is vertical with road direction, the first described video camera is connected with computing machine respectively by an image pick-up card with the second video camera, should comprise the following steps based on the passenger vehicle of video and lorry sorting technique:
Step one, first video camera and the second cameras capture video information within the vision, computing machine carries out image acquisition to the video information of the first video camera and the second camera acquisition respectively by image pick-up card, obtains the sequence of video images of the first video camera and the second camera acquisition;
Step 2, infrared vehicle separation vessel monitoring road on whether have vehicle process, if the headstock process of vehicle detected, then the information of the headstock process of this vehicle is passed to computing machine, computing machine start to camera acquisition to image information process; Note video frame number is N, and video adds up to M, and the initial value of M and N is 0; Perform step 3;
Step 3, computing machine utilizes the sequence of video images of the target tracking algorism of feature based angle point to the first camera acquisition to process:
(1) the first camera acquisition to sequence of video images in, selecting video image sequence current frame image, adopts Moravec algorithm to extract Corner, and centered by this angle point, chooses an image block as template;
(2) employing is followed the tracks of based on Block Matching Algorithm, in the next frame image of present frame, the pixel value of block onesize with above-mentioned template correspondence position and the pixel value of template are done difference, if the number that margin of image element is not 0 is greater than 5, then perform step 4, otherwise return step 3 continuation execution;
Step 4, computing machine to the second camera acquisition to sequence of video images process:
(1) demarcation of target area
The second camera acquisition to sequence of video images in, computer selecting current frame image, is divided into the identical region of three sizes by current frame image with vertical direction, chooses middle region as processing region;
(2) background subtraction is adopted processing region to be carried out to the segmentation of target
Adopt global threshold binarization method to process to each pixel of the processing region chosen, then the Region dividing after process is become the block that multiple size is identical, then carry out block-based binary conversion treatment to each piece;
(3) connected component labeling
Adopt eight neighborhood labeling algorithm to carry out connected component labeling to the image block after binary conversion treatment, and carry out the removal of connected domain and fill merging and obtain Contiguous graphics; Again Contiguous graphics is carried out to the closed operation process in morphologic filtering, obtain destination object;
(4) Band object detects
The geometric characteristic of evaluating objects object, calculates the aspect ratio of destination object, according to ratio, if the aspect ratio of destination object is greater than 25, then determines that this target is Band object;
(5) the tracking statistics of Band object
If destination object is not Band object, then video sum adds 1; If destination object is Band object, then video frame number N adds 1, and video sum adds 1; If infrared vehicle separation vessel detects that vehicle tail is by infrared vehicle separation vessel, then perform step 5, otherwise return step 3;
Step 5, computing machine stops the process to the sequence of video images that the first video camera and the second camera acquisition arrive, now ratio calculated k=N/M; If k > 50%, then judge that the vehicle of firm process is as passenger vehicle, otherwise be lorry.
2. as claimed in claim 1 based on passenger vehicle and the lorry sorting technique of video, it is characterized in that, the length of described LED is 1.5 ~ 2m, and width is 0.015m, the height on the distance ground, bottom of LED is 1.2 ~ 2m, and the light intensity of LED is 2500 ~ 3000cd.
3. as claimed in claim 1 based on passenger vehicle and the lorry sorting technique of video, it is characterized in that, after adopting Moravec algorithm to extract Corner in step 3, centered by this angle point, choose a size for the image block of 25*25 pixel is as template.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310326455.8A CN103413439B (en) | 2013-07-30 | 2013-07-30 | A kind of passenger vehicle based on video and lorry sorting technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310326455.8A CN103413439B (en) | 2013-07-30 | 2013-07-30 | A kind of passenger vehicle based on video and lorry sorting technique |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103413439A CN103413439A (en) | 2013-11-27 |
| CN103413439B true CN103413439B (en) | 2016-01-20 |
Family
ID=49606444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310326455.8A Expired - Fee Related CN103413439B (en) | 2013-07-30 | 2013-07-30 | A kind of passenger vehicle based on video and lorry sorting technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103413439B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574986A (en) * | 2014-12-22 | 2015-04-29 | 贵州中南交通科技有限公司 | Vehicle model identifier with radiating device |
| CN105702050A (en) * | 2016-04-22 | 2016-06-22 | 安徽皖通科技股份有限公司 | Highway over-limit and overload management control method |
| CN108417042A (en) * | 2017-09-18 | 2018-08-17 | 西安金路交通工程科技发展有限责任公司 | Car based on vehicle image and lorry sorting technique |
| CN108171982B (en) * | 2018-02-06 | 2019-05-21 | 江苏华正天和科技有限公司 | Crossing vehicular traffic vehicle monitor supervision platform |
| CN111833469B (en) * | 2019-04-18 | 2022-06-28 | 杭州海康威视数字技术股份有限公司 | Vehicle charging method and system applied to charging station |
| CN111145365A (en) * | 2019-12-17 | 2020-05-12 | 北京明略软件系统有限公司 | Method, device, computer storage medium and terminal for realizing classification processing |
| CN112002027A (en) * | 2020-09-04 | 2020-11-27 | 侯晓峰 | Highway charging method, device, terminal and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101783076A (en) * | 2010-02-04 | 2010-07-21 | 西安理工大学 | Method for quick vehicle type recognition under video monitoring mode |
| CN102637362A (en) * | 2012-04-01 | 2012-08-15 | 长安大学 | Tunnel vehicle type identification method based on video |
| CN103020582A (en) * | 2012-09-20 | 2013-04-03 | 苏州两江科技有限公司 | Method for computer to identify vehicle type by video image |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100261065B1 (en) * | 1997-12-30 | 2000-07-01 | 윤종용 | Vehicle classification method and apparatus using image analysis |
| JP5163460B2 (en) * | 2008-12-08 | 2013-03-13 | オムロン株式会社 | Vehicle type discrimination device |
-
2013
- 2013-07-30 CN CN201310326455.8A patent/CN103413439B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101783076A (en) * | 2010-02-04 | 2010-07-21 | 西安理工大学 | Method for quick vehicle type recognition under video monitoring mode |
| CN102637362A (en) * | 2012-04-01 | 2012-08-15 | 长安大学 | Tunnel vehicle type identification method based on video |
| CN103020582A (en) * | 2012-09-20 | 2013-04-03 | 苏州两江科技有限公司 | Method for computer to identify vehicle type by video image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103413439A (en) | 2013-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103413439B (en) | A kind of passenger vehicle based on video and lorry sorting technique | |
| CN102722704B (en) | Method and system for recognizing vehicle license plate by integrating video dynamic tracking | |
| CN103049787B (en) | A kind of demographic method based on head shoulder feature and system | |
| CN101510356B (en) | Video detection system and data processing device thereof, video detection method | |
| CN103279756B (en) | Vehicle detection based on integrated classifier analyzes system and determination method thereof | |
| TWI409718B (en) | Method of locating license plate of moving vehicle | |
| CN106127137A (en) | A kind of target detection recognizer based on 3D trajectory analysis | |
| CN103942560B (en) | A kind of high-resolution video vehicle checking method in intelligent traffic monitoring system | |
| CN102867417B (en) | Taxi anti-forgery system and taxi anti-forgery method | |
| CN102915433B (en) | Character combination-based license plate positioning and identifying method | |
| CN106682586A (en) | Method for real-time lane line detection based on vision under complex lighting conditions | |
| CN105404857A (en) | Infrared-based night intelligent vehicle front pedestrian detection method | |
| CN105608431A (en) | Vehicle number and traffic flow speed based highway congestion detection method | |
| CN103985182A (en) | Automatic public transport passenger flow counting method and system | |
| EP2813973B1 (en) | Method and system for processing video image | |
| CN102419820A (en) | Method for rapidly detecting car logo in videos and images | |
| CN105426894B (en) | Railway plug pin image detecting method and device | |
| CN103077387B (en) | Carriage of freight train automatic testing method in video | |
| CN102789686B (en) | Road traffic flow detecting method based on road surface brightness composite mode recognition | |
| CN104504363A (en) | Real-time identification method of sidewalk on the basis of time-space correlation | |
| CN103337175A (en) | Vehicle type recognition system based on real-time video steam | |
| CN109272482A (en) | A kind of urban road crossing vehicle queue detection system based on sequence image | |
| CN110633678A (en) | Rapid and efficient traffic flow calculation method based on video images | |
| CN103778790B (en) | A kind of vehicle flowrate square wave statistic law based on video sequence | |
| CN102610104A (en) | Onboard front vehicle detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160120 Termination date: 20170730 |