CN102043950A - Vehicle outline recognition method based on canny operator and marginal point statistic - Google Patents
Vehicle outline recognition method based on canny operator and marginal point statistic Download PDFInfo
- Publication number
- CN102043950A CN102043950A CN2010106125924A CN201010612592A CN102043950A CN 102043950 A CN102043950 A CN 102043950A CN 2010106125924 A CN2010106125924 A CN 2010106125924A CN 201010612592 A CN201010612592 A CN 201010612592A CN 102043950 A CN102043950 A CN 102043950A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- marginal point
- canny operator
- contour
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a vehicle outline recognition method based on canny operator and marginal point statistic, relating to the computer image recognition field, comprising firstly using an image preprocessing technology to convert a colour image into a gray image and performing the image smoothing and denoising; then using the canny operator to recognize the image marginal point, referring to image gradient computation, performing non-maximum suppression to the gradient amplitude, and performing dual-threshold computation to an initial marginal point; finally using the marginal point statistic method to obtain the vehicle outline region by scanning twice respectively in longitudinal and horizontal manner. A traditional image margin detection algorithm based on canny operator is combined with an outline recognition method based on marginal point statistic to preferably eliminate false marginal points and complete the margin notch so that the outline region judgment is more accurate, the outline region in the image can be accurately computed; the method is suitable for the statistic of traffic flow in highway monitoring.
Description
Technical field
The invention belongs to the computer picture recognition field, what be specifically related to is a kind of method that realizes vehicle ' s contour identification, is applicable to that vehicle flowrate detects and road monitoring.
Background technology
Vehicle flowrate is one of core index of road monitoring.Automatically the inspection vehicle flow relates to the vehicle individual identification, and core is the appearance profile identification of vehicle individuality.Identify current time cross section vehicle number by detecting vehicle ' s contour, thereby count vehicle flowrate in certain time range.The vehicle ' s contour edge detection algorithm is in image processing field, determines vehicle ' s contour in the image thereby mainly adopt canny operator, sobel operator, robert operator to carry out Image Edge-Detection.But because the complexity of vehicle class, color is various, the moving situation complexity, and the weather change, roadside construction etc. influences series of factors influences such as light source irradiation, makes vehicle individual identification difficulty increase.Wu Guowei [1] expands the Sobel operator, extends to the operator of 8 directions by the operator of both direction in length and breadth, makes that detected edge is more clear, and noise resisting ability strengthens.Vehicle ' s contour detects to be had and vital role aspect the differentiation type of vehicle.Vehicle during cuckoo people [2] will move carries out profile identification, mates with the typical car, passenger vehicle and the lorry sample that store, thereby judges car category, realizes the robotization of highway toll.
The Canny operator is used wider in rim detection, many applications such as [5], weld seam detection, rice rim detection, oranges and tangerines rim detection [4], ship target detection, LED Waffer edge [3] extraction from the general pattern rim detection to recognition of face.The improvement of Canny operator also from the fixed threshold to the adaptive threshold, the canny operator combines with the sobel operator, the canny operator combines with morphology etc.The main canny operator that utilizes rim detection than high precision and anti-ground unrest ability.
But the edge that is to use the Canny operator to obtain is thinner, and marginal point quantity itself is less, so that very difficult setting threshold judges whether a certain straight line is the edge in the marginal point statistic processes, thereby can't accurately extract image outline.The application of Canny operator in the vehicle edge profile is less, and Sun Lijun [6] has proposed the vehicle that edge extracting canny operator based on a kind of dynamic threshold of Otsu algorithm carries out the dynamic image sequence and carried out automatically effectively rim detection.Adopt the canny operator to add up with the vehicle ' s contour that the marginal point statistics combines, and based on still image, do not appear in the newspapers as yet.
List of references:
[1]. Wu Guowei, Xie Jinfa, Guo Zhiqiang. based on the vehicle ' s contour edge detection algorithm of Sobel operator. University Of Science and Technology Of He'nan's journal: natural science edition, 2009,30 (6): 38-41
[2]. cuckoo people, Gao Haojun. based on the model recognizing method of vehicle ' s contour location coupling. Yangzhou University's journal (natural science edition), 2007,10 (2): 62-65
[3]. Zhou Zhiyu, Liu Yingchun, Zhang Jianxin. based on the oranges and tangerines rim detection of self-adaptation Canny operator. Transactions of the Chinese Society of Agricultural Engineering, 2008,24 (3).
[4]. intelligence is few red, Li Jianyong, Wang Heng. extract based on the LED Waffer edge that improves the Canny algorithm. electromechanical engineering, 2010 (08): 10-14
[5]. in microwave, Chen Xiaojuan, Han Yu etc. based on the improvement Kirsch people face edge detection method of Canny algorithm. microcomputer information, 2009 (14): 301-302
[6]. Sun Lijun. a kind of vehicle target detection method, market modernization, 2007 (24) based on the Canny operator
Summary of the invention
Technical matters to be solved of the present invention is that the edge line of obtaining when carrying out Image Edge-Detection at the canny operator is thinner, marginal point is less, problems such as identification marginal point algorithm complexity, iterations are many, a kind of vehicle ' s contour recognition methods based on canny operator and marginal point statistics is proposed, utilize the marginal point statistical value to come significantly to strengthen preferably the contrastive feature of edge contour zone and background area, very fast, the accurate automobile edge contour zone of identifying.
The present invention adopts following technical scheme for achieving the above object:
Vehicle ' s contour recognition methods based on canny operator and marginal point statistics may further comprise the steps:
The jpeg image that step 1), input are identified vehicle carries out the gray processing processing, and the difference in the masked images between vehicle and the background obtains vehicle based on image gray;
Step 2), adopts the Gaussian image fuzzy filter that the gray level image of step 1) gained is carried out smoothing processing, filter out picture noise;
Step 3) adopts the canny operator to carry out gradient calculation, tries to achieve the Grad and the direction of each pixel in the gray level image;
Step 4) adopts the Grad of each pixel in the gray level image that step 3) obtains, and the gradient magnitude of each pixel is carried out non-maximum value suppress, and tentatively obtains image border point and gathers;
Step 5), the preliminary marginal point that step 4) is obtained carries out dual threshold calculating, and the marginal point of further refining is rejected false marginal point and completion emargintion, obtains accurate marginal point;
Step 6), the accurate marginal point that step 5) is obtained carries out statistical study, judges the vehicle ' s contour region, identifies the vehicle number that comprises in the image.
Further, the vehicle ' s contour recognition methods based on canny operator and marginal point statistics of the present invention, the R of each pixel of the jpeg image of step 1) employing vehicle, G, B three values are averaged and are obtained the gray level image of vehicle.
Further, vehicle ' s contour recognition methods based on canny operator and marginal point statistics of the present invention, step 2) described Gaussian image fuzzy filter adopts 5 * 5 convolution templates to ask the weighted mean computing that gray level image is carried out smoothing processing to the gradation of image matrix.
Further, vehicle ' s contour recognition methods based on canny operator and marginal point statistics of the present invention, the process that step 3) adopts the canny operator to carry out gradient calculation is: at first ask first order derivative in 5 * 5 fields of computed image horizontal stroke, vertical both direction, then according to the derivative composition gradient value and the direction of the canny operator of horizontal, longitudinal direction.
Further, vehicle ' s contour recognition methods based on canny operator and marginal point statistics of the present invention, step 4) is carried out non-maximum value inhibition employing 8 field modes to the Grad of each pixel, and being about to gradient direction is 8 directions according to average the dispersing of 360 degree, and spending every 45 is a direction.
Further, the vehicle ' s contour recognition methods based on canny operator and marginal point statistics of the present invention, the described dual threshold of step 5) is to adopt the k-menas clustering method to determine that wherein k is 3 according to gradient magnitude.
Further, the vehicle ' s contour recognition methods based on canny operator and marginal point statistics of the present invention, the described marginal point statistical study of step 6) adopt the mode of portraitlandscape scanning marginal point to carry out, and divide in length and breadth both direction to determine vehicle ' s contour.
The present invention adopts technique scheme to have following beneficial effect:
The present invention is directed to the identification in the zone of vehicle ' s contour, utilize marginal point system feature to strengthen the contrastive feature of edge contour and background, based on the method for detecting image edge of canny operator, very fast, standard identifies automobile edge contour zone.This method has shielded the ground unrest of picture preferably, and level and smooth pictorial information utilizes the marginal point statistical value to give prominence to the difference of marginal point and background dot, and this method can comparatively have recognition capability preferably to vehicle ' s contour in the rugged surroundings.With respect to traditional vehicle ' s contour recognizer based on the canny operator, can improve the accuracy of identification of edge contour at the bigger environment of background complexity, picture noise, be particularly suitable in the highway monitoring identification to the vehicle number.
Description of drawings:
Fig. 1 is based on the process flow diagram of the vehicle ' s contour recognition methods of canny operator and marginal point statistics;
Fig. 2 is that gradient discretize direction and non-maximum value suppress the operator synoptic diagram;
Fig. 3 is based on the vehicle ' s contour identification detail flowchart of marginal point statistics.
Specific embodiments:
Be described in further detail below in conjunction with the enforcement of accompanying drawing technical scheme:
In conjunction with process flow diagram and case study on implementation the vehicle ' s contour recognition methods based on canny operator and marginal point statistics of the present invention is described in further detail.
The algorithm that the implementation case adopts the canny operator to combine with the marginal point statistics carries out vehicle ' s contour identification, and then counts vehicle number and vehicle flow.As shown in Figure 1, this method comprises following steps:
Step 10, the image of input is converted into the JPG form, the threshold value that the gradient maximum value in the identification of canny Operator Image Edge suppresses is set, the used height threshold value of endpoint detections is set, image smoothing operator and gradient calculation operator are set, the input and output path of image is set.
Whether step 20 adopts the mode that file is detected, and judges whether the input picture file is legal, be the picture format that this method can be discerned processing.
Step 30 realizes the pre-service to image, and main the employing carried out coloured image the gray processing processing and the gradation of image value is carried out smoothing processing.Gray processing is handled the processing formula that relates to:
, R in the formula, G, B are the RGB information of each pixel of picture, and Gr is by being asked gray-scale value.Gray scale smoothly adopts the Gaussian Blur operator, asks the weighted mean computing to realize by using following 5*5 convolution template to the gradation of image matrix.
Step 40 with the gray-scale value behind Gaussian Blur that step 30 obtains, adopts the canny operator to carry out marginalisation and detects.At first adopt the derivative operation (field subtraction) of Gauss's template discretize to obtain x, y both direction cope match-plate pattern operator is obtained x respectively, the first order derivative on the y both direction, thereby the gradient of trying to achieve and gradient direction; Secondly, gradient direction is dispersed, carry out non-maximum value and suppress, obtain the wide edge aggregation of an about pixel.
Gradient discretize direction and non-maximum value suppress operator as shown in Figure 2.Wherein, Fig. 2 (a) expression gradient is discrete according to per 45 degree to be a direction, positive and negative two aspects of the wherein digital identical same direction of expression; Fig. 2 (b) expression is replaced 8 directions on justifying with 8 adjacent pixels; Eight discrete directions on Fig. 2 (c) expression circle and the corresponding relation of pixel.The basic thought that non-maximum value suppresses is: the Grad of pixel and make comparisons along two points (equidirectional two points) of gradient line, if this Grad is bigger unlike the Grad of these two points, then the big Grad in these 2 is made as the Grad of this pixel, otherwise, the Grad of this pixel remains unchanged, and the Grad of realizing this pixel like this is a Grad maximum on its gradient direction.
Step 50 is carried out just cutting apart of dual threshold with the comparatively rough edge point set that step 40 obtains, and adopting the described dual threshold of step 5) is to adopt the k-menas clustering method that the pixel gradient magnitude is carried out cluster analysis according to gradient magnitude, and wherein k is 3; By cluster analysis, pixel is divided into 3 big classes according to gradient magnitude, wherein the lower limit of the class that gradient magnitude is bigger is made as high threshold, and gradient magnitude is made as lowest threshold than the upper limit of group.With the high threshold set is basic edge aggregation, thereby utilizes the method for low threshold value set completion high threshold set to obtain marginal points information more accurately to improve edge aggregation.And above result is converted into edge binary map (pixel of marginal point for white).
Step 60 by above marginal point is analyzed, identifies the appearance profile of vehicle.Adopt in length and breadth both direction to carry out the marginal point statistics, draw the vehicle ' s contour zone.
As shown in Figure 3, as follows based on the vehicle ' s contour identification process of marginal point statistics:
Step 601 is provided with xLimit, yLimit and W, and four threshold values of H, xLimit, yLimit are respectively applied for transversal scanning, longitudinal scanning and judge the profile border, and W, H are used to reject laterally, the rejecting of profile noise during longitudinal scanning.
Step 602, transversal scanning, scan picture marginal point matrix from left to right with the wide ordinate of n pixel, if the marginal point sum of all pixels that n bar ordinate passes through begins the pixel greater than threshold value xLimit(from the somewhere), suppose that then this place is the contour area edge, then by setting profile target width threshold value W(pixel) to distinguish profile target and background noise.
Step 603, after transversal scanning being obtained the left and right edges of each contour area, scan from top to bottom between each profile target left and right edges with the wide horizontal line of n pixel again, if the edge pixel sum that passes through of n bar horizontal line begin from the somewhere greater than (less than) threshold value yLimit(pixel), suppose that then it is the contour area edge, then by setting profile object height threshold value H(pixel) to distinguish profile target and background noise.
Step 604 is added to the contour area that obtains in the coloured image.
Claims (7)
1. based on the vehicle ' s contour recognition methods of canny operator and marginal point statistics, it is characterized in that, may further comprise the steps:
The jpeg image that step 1), input are identified vehicle carries out the gray processing processing, and the difference in the masked images between vehicle and the background obtains vehicle based on image gray;
Step 2), adopts the Gaussian image fuzzy filter that the gray level image of step 1) gained is carried out smoothing processing, filter out picture noise;
Step 3) adopts the canny operator to carry out gradient calculation, tries to achieve the Grad and the direction of each pixel in the gray level image;
Step 4) adopts the Grad of each pixel in the gray level image that step 3) obtains, and the gradient magnitude of each pixel is carried out non-maximum value suppress, and tentatively obtains image border point and gathers;
Step 5), the preliminary marginal point that step 4) is obtained carries out dual threshold calculating, and the marginal point of further refining is rejected false marginal point and completion emargintion, obtains accurate marginal point;
Step 6), the accurate marginal point that step 5) is obtained carries out statistical study, judges the vehicle ' s contour region, identifies the vehicle number that comprises in the image.
2. the vehicle ' s contour recognition methods based on canny operator and marginal point statistics according to claim 1 is characterized in that: the R of each pixel of the jpeg image of step 1) employing vehicle, and G, B three values are averaged and are obtained the gray level image of vehicle.
3. the vehicle ' s contour recognition methods based on canny operator and marginal point statistics according to claim 1 is characterized in that: step 2) described Gaussian image fuzzy filter adopts 5 * 5 convolution templates to ask the weighted mean computing that gray level image is carried out smoothing processing to the gradation of image matrix.
4. the vehicle ' s contour recognition methods based on canny operator and marginal point statistics according to claim 1, it is characterized in that: the process that step 3) adopts the canny operator to carry out gradient calculation is: at first ask first order derivative in 5 * 5 fields of computed image horizontal stroke, vertical both direction, then according to the derivative composition gradient value and the direction of the canny operator of horizontal, longitudinal direction.
5. the vehicle ' s contour recognition methods based on canny operator and marginal point statistics according to claim 1, it is characterized in that: step 4) is carried out non-maximum value inhibition employing 8 field modes to the Grad of each pixel, being about to gradient direction is 8 directions according to average the dispersing of 360 degree, is a direction every 45 degree.
6. the vehicle ' s contour recognition methods based on canny operator and marginal point statistics according to claim 1 is characterized in that: the described dual threshold of step 5) is to adopt the k-menas clustering method to determine that wherein k is 3 according to gradient magnitude.
7. the vehicle ' s contour recognition methods based on canny operator and marginal point statistics according to claim 1, it is characterized in that: the described marginal point statistical study of step 6) adopts the mode of portraitlandscape scanning marginal point to carry out, and divides in length and breadth both direction to determine vehicle ' s contour.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106125924A CN102043950B (en) | 2010-12-30 | 2010-12-30 | Vehicle outline recognition method based on canny operator and marginal point statistic |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106125924A CN102043950B (en) | 2010-12-30 | 2010-12-30 | Vehicle outline recognition method based on canny operator and marginal point statistic |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102043950A true CN102043950A (en) | 2011-05-04 |
| CN102043950B CN102043950B (en) | 2012-11-28 |
Family
ID=43910078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010106125924A Expired - Fee Related CN102043950B (en) | 2010-12-30 | 2010-12-30 | Vehicle outline recognition method based on canny operator and marginal point statistic |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102043950B (en) |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324134A (en) * | 2011-09-19 | 2012-01-18 | 广州广电运通金融电子股份有限公司 | Valuable document identification method and device |
| CN102982534A (en) * | 2012-11-01 | 2013-03-20 | 北京理工大学 | Canny edge detection dual threshold acquiring method based on chord line tangent method |
| CN103116757A (en) * | 2013-01-30 | 2013-05-22 | 北京科技大学 | Three-dimension information restoration and extraction method for identifying spilled articles on roads |
| CN103208005A (en) * | 2012-01-13 | 2013-07-17 | 富士通株式会社 | Object recognition method and object recognition device |
| CN103258434A (en) * | 2013-04-25 | 2013-08-21 | 广州中国科学院软件应用技术研究所 | Image border detecting system based on video traffic flow detection and vehicle identification |
| CN103577828A (en) * | 2013-11-22 | 2014-02-12 | 中国科学院自动化研究所 | Road detection method based on edge feature |
| CN105261017A (en) * | 2015-10-14 | 2016-01-20 | 长春工业大学 | Method for extracting regions of interest of pedestrian by using image segmentation method on the basis of road restriction |
| CN105615070A (en) * | 2014-11-04 | 2016-06-01 | 广西北海利博盛安全用品有限公司 | Methods for acquiring sizes of hands and manufacturing gloves |
| CN106228568A (en) * | 2016-10-11 | 2016-12-14 | 北京京东尚科信息技术有限公司 | Blurred picture detection method and device |
| CN106384358A (en) * | 2016-08-30 | 2017-02-08 | 南京明辉创鑫电子科技有限公司 | Edge point self-similarity based irregular image recognition method |
| CN104008553B (en) * | 2014-06-17 | 2017-03-22 | 武汉武大卓越科技有限责任公司 | Crack detection method with image gradient information and watershed method conflated |
| CN106651890A (en) * | 2016-08-30 | 2017-05-10 | 南京鑫和汇通电子科技有限公司 | Metal reflection image identification technology based on edge point self-similarity, and TEDS system |
| CN107273884A (en) * | 2017-05-05 | 2017-10-20 | 广州恒巨信息科技有限公司 | A kind of License Plate Identification method based on mobile terminal camera |
| CN107392930A (en) * | 2017-08-07 | 2017-11-24 | 重庆邮电大学 | A kind of quantum Canny edge detection methods |
| CN108171696A (en) * | 2017-12-29 | 2018-06-15 | 深圳开立生物医疗科技股份有限公司 | A kind of placenta detection method and device |
| CN108364245A (en) * | 2018-02-21 | 2018-08-03 | 韩明泽 | A kind of anti-cheating management system in examination hall |
| CN108407759A (en) * | 2018-05-21 | 2018-08-17 | 辽宁工业大学 | Automobile intelligent starting module based on recognition of face and startup method |
| CN109035198A (en) * | 2018-06-07 | 2018-12-18 | 华南理工大学 | The LED detection method of outdoor visible light communication based on edge detection |
| CN109426825A (en) * | 2017-08-31 | 2019-03-05 | 北京图森未来科技有限公司 | A kind of detection method and device of object closed outline |
| CN109520678A (en) * | 2018-12-26 | 2019-03-26 | 浙江工业大学 | A kind of pressure maintaining detection method for pressure vessel air tightness test |
| CN109636824A (en) * | 2018-12-20 | 2019-04-16 | 巢湖学院 | A kind of multiple target method of counting based on image recognition technology |
| CN109961475A (en) * | 2017-12-22 | 2019-07-02 | 深圳市优必选科技有限公司 | Image direction recognition methods, device, terminal device and readable storage medium storing program for executing |
| CN110084825A (en) * | 2019-04-16 | 2019-08-02 | 上海岚豹智能科技有限公司 | A kind of method and system based on image edge information navigation |
| CN111062317A (en) * | 2019-12-16 | 2020-04-24 | 中国计量大学上虞高等研究院有限公司 | Method and system for cutting edges of scanned document |
| CN111127494A (en) * | 2019-11-12 | 2020-05-08 | 中国矿业大学 | Expressway truck weight limit identification method based on image processing |
| CN111340966A (en) * | 2019-12-12 | 2020-06-26 | 山东中创软件工程股份有限公司 | Vehicle detection method, device and system |
| CN111695615A (en) * | 2020-05-28 | 2020-09-22 | 平安科技（深圳）有限公司 | Vehicle damage assessment method and device based on artificial intelligence, electronic equipment and medium |
| CN112308873A (en) * | 2020-11-09 | 2021-02-02 | 西安工程大学 | Edge detection method for multi-scale Gabor wavelet PCA fusion image |
| CN112634269A (en) * | 2021-01-14 | 2021-04-09 | 华东交通大学 | Rail vehicle body detection method |
| CN112991374A (en) * | 2021-03-31 | 2021-06-18 | 新疆爱华盈通信息技术有限公司 | Canny algorithm-based edge enhancement method, device, equipment and storage medium |
| CN113075709A (en) * | 2021-03-24 | 2021-07-06 | 刘成 | Vehicle-mounted satellite navigation method and device, storage medium and processor |
| CN113139526A (en) * | 2021-05-21 | 2021-07-20 | 一汽奔腾轿车有限公司 | Parking berth line identification method based on OpenCV |
| CN113326720A (en) * | 2020-02-29 | 2021-08-31 | 湖南超能机器人技术有限公司 | Image blur detection method and device based on contour depth learning |
| CN113588663A (en) * | 2021-08-03 | 2021-11-02 | 上海圭目机器人有限公司 | Pipeline defect identification and information extraction method |
| CN113902667A (en) * | 2021-08-23 | 2022-01-07 | 浙大宁波理工学院 | Thread turning identification method and system for machine vision |
| CN114387572A (en) * | 2022-01-11 | 2022-04-22 | 杭州电子科技大学 | AI technology-based red light running illegal vehicle matching method in traffic law enforcement image |
| CN114882059A (en) * | 2022-07-01 | 2022-08-09 | 深圳市远湖科技有限公司 | Dimension measuring method, device and equipment based on image analysis and storage medium |
| CN115035350A (en) * | 2022-06-29 | 2022-09-09 | 电子科技大学 | Method for detecting small targets against air ground and ground background based on edge detection enhancement |
| CN115082456A (en) * | 2022-07-27 | 2022-09-20 | 煤炭科学研究总院有限公司 | Coal mine belt conveyor fault diagnosis method and device |
| CN115731253A (en) * | 2022-11-16 | 2023-03-03 | 刘梓航 | Image edge extraction method, system, equipment and medium |
| CN117523036A (en) * | 2024-01-05 | 2024-02-06 | 深圳大学 | Planar house type graph structured reconstruction method, device, equipment and medium |
| CN117523526A (en) * | 2023-11-02 | 2024-02-06 | 深圳鑫扬明科技有限公司 | Vehicle detection system and method based on machine vision |
| CN117523036B (en) * | 2024-01-05 | 2024-06-28 | 深圳大学 | Planar house type graph structured reconstruction method, device, equipment and medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103630070A (en) * | 2013-04-08 | 2014-03-12 | 苏州工业园区凯艺精密科技有限公司 | Detection method for image detector and image detector |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1984236A (en) * | 2005-12-14 | 2007-06-20 | 浙江工业大学 | Method for collecting characteristics in telecommunication flow information video detection |
| CN1996346A (en) * | 2005-12-29 | 2007-07-11 | 电子科技大学 | Vehicle recognition algorithm based on contour |
-
2010
- 2010-12-30 CN CN2010106125924A patent/CN102043950B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1984236A (en) * | 2005-12-14 | 2007-06-20 | 浙江工业大学 | Method for collecting characteristics in telecommunication flow information video detection |
| CN1996346A (en) * | 2005-12-29 | 2007-07-11 | 电子科技大学 | Vehicle recognition algorithm based on contour |
Non-Patent Citations (1)
| Title |
|---|
| 《仪器仪表学报》 20100630 齐美彬等 "一种基于车辆遮挡模型的车流量统计算法" 1335-1341 1-7 第31卷, 第6期 * |
Cited By (60)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324134A (en) * | 2011-09-19 | 2012-01-18 | 广州广电运通金融电子股份有限公司 | Valuable document identification method and device |
| CN103208005A (en) * | 2012-01-13 | 2013-07-17 | 富士通株式会社 | Object recognition method and object recognition device |
| WO2013104322A1 (en) * | 2012-01-13 | 2013-07-18 | Fujitsu Limited | Object recognizing method and object recognizing device |
| CN102982534A (en) * | 2012-11-01 | 2013-03-20 | 北京理工大学 | Canny edge detection dual threshold acquiring method based on chord line tangent method |
| CN103116757A (en) * | 2013-01-30 | 2013-05-22 | 北京科技大学 | Three-dimension information restoration and extraction method for identifying spilled articles on roads |
| CN103116757B (en) * | 2013-01-30 | 2016-12-28 | 北京科技大学 | A kind of three-dimensional information restores the road extracted and spills thing recognition methods |
| CN103258434A (en) * | 2013-04-25 | 2013-08-21 | 广州中国科学院软件应用技术研究所 | Image border detecting system based on video traffic flow detection and vehicle identification |
| CN103577828A (en) * | 2013-11-22 | 2014-02-12 | 中国科学院自动化研究所 | Road detection method based on edge feature |
| CN104008553B (en) * | 2014-06-17 | 2017-03-22 | 武汉武大卓越科技有限责任公司 | Crack detection method with image gradient information and watershed method conflated |
| CN105615070A (en) * | 2014-11-04 | 2016-06-01 | 广西北海利博盛安全用品有限公司 | Methods for acquiring sizes of hands and manufacturing gloves |
| CN105261017A (en) * | 2015-10-14 | 2016-01-20 | 长春工业大学 | Method for extracting regions of interest of pedestrian by using image segmentation method on the basis of road restriction |
| CN106651890B (en) * | 2016-08-30 | 2019-05-03 | 南京鑫和汇通电子科技有限公司 | Metal reflective image recognition and TEDS system based on marginal point self-similarity |
| CN106651890A (en) * | 2016-08-30 | 2017-05-10 | 南京鑫和汇通电子科技有限公司 | Metal reflection image identification technology based on edge point self-similarity, and TEDS system |
| CN106384358A (en) * | 2016-08-30 | 2017-02-08 | 南京明辉创鑫电子科技有限公司 | Edge point self-similarity based irregular image recognition method |
| CN106384358B (en) * | 2016-08-30 | 2019-03-29 | 南京明辉创鑫电子科技有限公司 | The recognition methods of irregular image based on marginal point self-similarity |
| CN106228568A (en) * | 2016-10-11 | 2016-12-14 | 北京京东尚科信息技术有限公司 | Blurred picture detection method and device |
| CN107273884A (en) * | 2017-05-05 | 2017-10-20 | 广州恒巨信息科技有限公司 | A kind of License Plate Identification method based on mobile terminal camera |
| CN107392930A (en) * | 2017-08-07 | 2017-11-24 | 重庆邮电大学 | A kind of quantum Canny edge detection methods |
| CN107392930B (en) * | 2017-08-07 | 2020-09-01 | 重庆邮电大学 | Quantum Canny edge detection method |
| CN109426825A (en) * | 2017-08-31 | 2019-03-05 | 北京图森未来科技有限公司 | A kind of detection method and device of object closed outline |
| CN109961475A (en) * | 2017-12-22 | 2019-07-02 | 深圳市优必选科技有限公司 | Image direction recognition methods, device, terminal device and readable storage medium storing program for executing |
| CN108171696B (en) * | 2017-12-29 | 2020-12-18 | 深圳开立生物医疗科技股份有限公司 | Placenta detection method and device |
| CN108171696A (en) * | 2017-12-29 | 2018-06-15 | 深圳开立生物医疗科技股份有限公司 | A kind of placenta detection method and device |
| CN108364245A (en) * | 2018-02-21 | 2018-08-03 | 韩明泽 | A kind of anti-cheating management system in examination hall |
| CN108407759A (en) * | 2018-05-21 | 2018-08-17 | 辽宁工业大学 | Automobile intelligent starting module based on recognition of face and startup method |
| CN109035198A (en) * | 2018-06-07 | 2018-12-18 | 华南理工大学 | The LED detection method of outdoor visible light communication based on edge detection |
| CN109636824A (en) * | 2018-12-20 | 2019-04-16 | 巢湖学院 | A kind of multiple target method of counting based on image recognition technology |
| CN109636824B (en) * | 2018-12-20 | 2022-10-11 | 巢湖学院 | Multi-target counting method based on image recognition technology |
| CN109520678A (en) * | 2018-12-26 | 2019-03-26 | 浙江工业大学 | A kind of pressure maintaining detection method for pressure vessel air tightness test |
| CN110084825A (en) * | 2019-04-16 | 2019-08-02 | 上海岚豹智能科技有限公司 | A kind of method and system based on image edge information navigation |
| CN111127494B (en) * | 2019-11-12 | 2023-11-24 | 中国矿业大学 | Highway truck weight limiting identification method based on image processing |
| CN111127494A (en) * | 2019-11-12 | 2020-05-08 | 中国矿业大学 | Expressway truck weight limit identification method based on image processing |
| CN111340966A (en) * | 2019-12-12 | 2020-06-26 | 山东中创软件工程股份有限公司 | Vehicle detection method, device and system |
| CN111340966B (en) * | 2019-12-12 | 2022-03-08 | 山东中创软件工程股份有限公司 | Vehicle detection method, device and system |
| CN111062317A (en) * | 2019-12-16 | 2020-04-24 | 中国计量大学上虞高等研究院有限公司 | Method and system for cutting edges of scanned document |
| CN113326720A (en) * | 2020-02-29 | 2021-08-31 | 湖南超能机器人技术有限公司 | Image blur detection method and device based on contour depth learning |
| CN111695615A (en) * | 2020-05-28 | 2020-09-22 | 平安科技（深圳）有限公司 | Vehicle damage assessment method and device based on artificial intelligence, electronic equipment and medium |
| WO2021151278A1 (en) * | 2020-05-28 | 2021-08-05 | 平安科技（深圳）有限公司 | Method and apparatus for vehicle damage assessment based on artificial intelligence, electronic device, and medium |
| CN112308873B (en) * | 2020-11-09 | 2024-04-05 | 西安工程大学 | Edge detection method for multi-scale Gabor wavelet PCA fusion image |
| CN112308873A (en) * | 2020-11-09 | 2021-02-02 | 西安工程大学 | Edge detection method for multi-scale Gabor wavelet PCA fusion image |
| CN112634269B (en) * | 2021-01-14 | 2023-12-26 | 华东交通大学 | Railway vehicle body detection method |
| CN112634269A (en) * | 2021-01-14 | 2021-04-09 | 华东交通大学 | Rail vehicle body detection method |
| CN113075709A (en) * | 2021-03-24 | 2021-07-06 | 刘成 | Vehicle-mounted satellite navigation method and device, storage medium and processor |
| CN112991374B (en) * | 2021-03-31 | 2024-05-24 | 芯算一体(深圳)科技有限公司 | Canny algorithm-based edge enhancement method, canny algorithm-based edge enhancement device, canny algorithm-based edge enhancement equipment and storage medium |
| CN112991374A (en) * | 2021-03-31 | 2021-06-18 | 新疆爱华盈通信息技术有限公司 | Canny algorithm-based edge enhancement method, device, equipment and storage medium |
| CN113139526A (en) * | 2021-05-21 | 2021-07-20 | 一汽奔腾轿车有限公司 | Parking berth line identification method based on OpenCV |
| CN113588663A (en) * | 2021-08-03 | 2021-11-02 | 上海圭目机器人有限公司 | Pipeline defect identification and information extraction method |
| CN113588663B (en) * | 2021-08-03 | 2024-01-23 | 上海圭目机器人有限公司 | Pipeline defect identification and information extraction method |
| CN113902667B (en) * | 2021-08-23 | 2022-06-14 | 浙大宁波理工学院 | Thread turning identification method and system for machine vision |
| CN113902667A (en) * | 2021-08-23 | 2022-01-07 | 浙大宁波理工学院 | Thread turning identification method and system for machine vision |
| CN114387572B (en) * | 2022-01-11 | 2024-04-09 | 杭州电子科技大学 | Traffic law enforcement image based on AI technology for matching vehicles running red light and illegal |
| CN114387572A (en) * | 2022-01-11 | 2022-04-22 | 杭州电子科技大学 | AI technology-based red light running illegal vehicle matching method in traffic law enforcement image |
| CN115035350A (en) * | 2022-06-29 | 2022-09-09 | 电子科技大学 | Method for detecting small targets against air ground and ground background based on edge detection enhancement |
| CN115035350B (en) * | 2022-06-29 | 2024-05-07 | 电子科技大学 | Edge detection enhancement-based method for detecting small objects on air-ground and ground background |
| CN114882059A (en) * | 2022-07-01 | 2022-08-09 | 深圳市远湖科技有限公司 | Dimension measuring method, device and equipment based on image analysis and storage medium |
| CN115082456A (en) * | 2022-07-27 | 2022-09-20 | 煤炭科学研究总院有限公司 | Coal mine belt conveyor fault diagnosis method and device |
| CN115731253A (en) * | 2022-11-16 | 2023-03-03 | 刘梓航 | Image edge extraction method, system, equipment and medium |
| CN117523526A (en) * | 2023-11-02 | 2024-02-06 | 深圳鑫扬明科技有限公司 | Vehicle detection system and method based on machine vision |
| CN117523036A (en) * | 2024-01-05 | 2024-02-06 | 深圳大学 | Planar house type graph structured reconstruction method, device, equipment and medium |
| CN117523036B (en) * | 2024-01-05 | 2024-06-28 | 深圳大学 | Planar house type graph structured reconstruction method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102043950B (en) | 2012-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102043950B (en) | Vehicle outline recognition method based on canny operator and marginal point statistic | |
| CN106651872B (en) | Pavement crack identification method and system based on Prewitt operator | |
| CN105261017B (en) | The method that image segmentation based on road surface constraint extracts pedestrian's area-of-interest | |
| CN104715239B (en) | A kind of vehicle color identification method based on defogging processing and weight piecemeal | |
| CN108765443B (en) | Sign enhancement processing method for self-adaptive color threshold segmentation | |
| CN108108761A (en) | A kind of rapid transit signal lamp detection method based on depth characteristic study | |
| CN105913041B (en) | It is a kind of based on the signal lamp recognition methods demarcated in advance | |
| CN103198315B (en) | Based on the Character Segmentation of License Plate of character outline and template matches | |
| CN107220624A (en) | A kind of method for detecting human face based on Adaboost algorithm | |
| CN107273896A (en) | A kind of car plate detection recognition methods based on image recognition | |
| CN106650553A (en) | License plate recognition method and system | |
| CN105809138A (en) | Road warning mark detection and recognition method based on block recognition | |
| CN105160691A (en) | Color histogram based vehicle body color identification method | |
| Duan et al. | A WBC segmentation methord based on HSI color space | |
| CN103425989B (en) | Vehicle color identification method and system based on significance analysis | |
| CN109993099A (en) | A kind of lane line drawing recognition methods based on machine vision | |
| CN104751142A (en) | Natural scene text detection algorithm based on stroke features | |
| CN102880863B (en) | Method for positioning license number and face of driver on basis of deformable part model | |
| CN103927548B (en) | Novel vehicle collision avoiding brake behavior detection method | |
| CN107315990B (en) | Pedestrian detection algorithm based on XCS-LBP characteristics | |
| CN105893960A (en) | Road traffic sign detecting method based on phase symmetry | |
| CN106650728A (en) | Shadow license plate image binarization method | |
| CN108734131A (en) | A kind of traffic sign symmetry detection methods in image | |
| CN102610104B (en) | Onboard front vehicle detection method | |
| Ingole et al. | Characters feature based Indian vehicle license plate detection and recognition |
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 |
Granted publication date: 20121128 Termination date: 20151230 |
|
| EXPY | Termination of patent right or utility model |