CN105512662A - Detection method and apparatus for unlicensed vehicle - Google Patents
Detection method and apparatus for unlicensed vehicle Download PDFInfo
- Publication number
- CN105512662A CN105512662A CN201510850001.XA CN201510850001A CN105512662A CN 105512662 A CN105512662 A CN 105512662A CN 201510850001 A CN201510850001 A CN 201510850001A CN 105512662 A CN105512662 A CN 105512662A
- Authority
- CN
- China
- Prior art keywords
- license plate
- sub
- vehicle
- region
- extracting
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims 3
- 230000000694 effects Effects 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 4
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a detection method and apparatus for an unlicensed vehicle. The method comprises: a vehicle in a video is detected and a vehicle sub image in the video is extracted; pretreatment is carried out on the detected sub image; image edge extraction is carried out on the sub image after the pretreatment; for an edge point, a sub image of a small area near the edge point is extracted and a color feature of the sub image is extracted; a vehicle color model is used for carrying out determination and whether the extracted sub image is a candidate license plate area is detected, all candidate license plate areas meeting the requirement are detected, and an area with the best matching effect among all candidate license plate areas is found and is determined as a license plate area; and if no license plate area is detected, the vehicle is determined to be an unlicensed vehicle. Therefore, a clear license plate can be identified and adaptability to the blurred license plate is also high, so that the license plate identification rate is improved and the effect of detection on the unlicensed vehicle is good.
Description
Technical Field
The invention belongs to the field of computer vision, and particularly relates to a method and a device for detecting a unlicensed vehicle.
Background
With the development of society and the progress of science and technology, the quantity of cars in the world is rapidly increased, a series of traffic problems appear, and great pressure is brought to the traffic management of cities.
At present, license plate recognition, violation detection, flow statistics and traffic investigation are all important components in an intelligent traffic system.
Traffic surveys include traffic volume, vehicle speed, vehicle type statistics, etc., where detection of a unlicensed vehicle is of concern. On the one hand, the number of the unlicensed vehicles can be counted, on the other hand, data analysis can be performed according to detection results, so that the owners of the unlicensed vehicles can be tracked, and traffic management can be performed more effectively.
Disclosure of Invention
The invention aims to provide a method for detecting a unlicensed vehicle, which can realize intellectualization, automation and simplification of traffic management.
To achieve the above object, in one aspect, the present invention provides a method for detecting a unlicensed vehicle, the method including the steps of:
detecting vehicles in the video, and extracting vehicle sub-images in the video; preprocessing the detected sub-images; carrying out image edge extraction on the preprocessed sub-images; for the edge point, extracting a small block area subimage near the edge point, and extracting the color characteristic of the subimage; judging by using a license plate color model, and detecting whether the extracted sub-image is a candidate license plate area; detecting all candidate license plate regions which meet the conditions, finding the most matched region in all the candidate license plate regions, and determining the region as a license plate region; and if the license plate area is not detected, judging that the vehicle is a non-license vehicle.
Preferably, the step of detecting vehicles in the video and extracting sub-images of vehicles in the video includes: detecting vehicles in the video through the vehicle model, and extracting vehicle sub-images in the video; the vehicle model is obtained by extracting a haar feature of a vehicle and then learning by using an Andubbs adaboost classifier, and the haar feature and the adaboost classifier are also used for detecting the vehicle in the video during detection.
Haar features, a commonly used feature description operator known to those skilled in the art (i.e., in the field of computer vision).
Adaboost is an iterative algorithm known to those skilled in the art, and its core idea is to train different classifiers (weak classifiers) for the same training set, and then to assemble these weak classifiers to form a stronger final classifier (strong classifier).
Preferably, the preprocessing the detected sub-images comprises: smoothing and stretching the sub-images of the vehicle, thereby eliminating the effects of illumination and noise.
Preferably, the step of extracting the image edge of the preprocessed sub-image includes: and performing vertical edge detection on the preprocessed sub-images by adopting a Sobel operator. The Sobel operator is an important processing method in the field of computer vision, is mainly used for obtaining the first-order gradient of a digital image, and is used for detecting the vertical edge of a preprocessed sub-image in the invention.
Preferably, for an edge point, the extracting a sub-image of a small block region near the edge point and extracting color features of the sub-image comprises: and carrying out binarization on the sub-image of the small block region, respectively counting a color histogram of a corresponding point of a black region and a color histogram of a corresponding point of a white region after binarization, wherein the used color space is a Hue Saturation Value (HSV) color space, and combining the hue saturation value and the HSV color space to obtain the color characteristics of the extraction block. The binarization processing mentioned above is to set the gray value of the pixel point on the sub-image of the small block region to 0 or 255, that is, to extract the black region and the white region in the sub-image of the small block region.
Preferably, the step of distinguishing by using the license plate color model and detecting whether the extracted sub-image is a candidate license plate region comprises: and judging whether the sub-image of the current small area is the license plate area or not according to the trained license plate color model.
Preferably, the color models are classified into four types in total in the training phase: carrying out binarization on samples, converting a color space from RGB to HSV, respectively counting histograms of points corresponding to a black-white area after binarization, combining the histograms to obtain the characteristics of each sample, and then training by using an SVM classifier; in the detection stage, as the SVM classifier returns a matching value, for each block of region, if the matching value is found to be large through detection, the block of region is considered as a candidate license plate region, otherwise, the block of region is not a license plate region.
Preferably, the step of detecting all candidate license plate regions meeting the conditions and finding the most matched region in all candidate license plate regions, and determining the license plate region comprises: and merging adjacent candidate license plate regions, judging the matching degree of the license plate through a color model, and considering the region with the highest matching degree as a real license plate region.
In another aspect, the present invention provides a unlicensed vehicle detecting apparatus, including: the device comprises a first detection unit, a processing unit, a first extraction unit, a second detection unit and a judgment unit. Wherein,
the first detection unit is used for detecting vehicles in the video and extracting sub-images of the vehicles in the video;
the processing unit is used for preprocessing the detected sub-images;
the first extraction unit is used for extracting the image edge of the preprocessed sub-image;
the second extraction unit is used for extracting the sub-image of the small block area near the edge point and extracting the color characteristic of the sub-image for the edge point;
the second detection unit is used for distinguishing by using the license plate color model and detecting whether the extracted sub-images are candidate license plate areas;
the judging unit is used for detecting all candidate license plate areas meeting the conditions, finding the most matched area in all the candidate license plate areas and determining the area as a license plate area; and if the license plate area is not detected, judging that the vehicle is a non-license vehicle.
The invention uses the vehicle model to detect the vehicle, further uses the color model to judge the license plate, uses the color model to detect the license plate, can identify the clear license plate, has good adaptability to the fuzzy license plate, improves the identification rate of the license plate identification, and further has good effect on the license plate-free vehicle detection.
Drawings
FIG. 1 is a block diagram illustrating a flow chart of a method for detecting a unlicensed vehicle according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of a structure of a detecting device for a unlicensed vehicle according to an embodiment of the present invention.
Detailed Description
Other features, characteristics and advantages of the present invention will become more apparent from the following detailed description of embodiments of the present invention, which is to be read in connection with the accompanying drawings.
Fig. 1 is a schematic block diagram of a flow of a method for detecting a unlicensed vehicle according to an embodiment of the present invention. As shown in fig. 1, the method comprises steps 101-107:
step 101, detecting vehicles in the video, and extracting sub-images of the vehicles in the video.
Detecting vehicles in the video by using a vehicle model, and in the training phase of the vehicle model: and sorting a large number of positive sample vehicle images and negative sample non-vehicle images, extracting haar characteristics of the samples, and training by combining an adaboost classifier to obtain a second-class discrimination model. In the detection stage, the same features and classifiers and the trained models are used for detecting the vehicles, and sub-images of the vehicles in the video are extracted.
Step 102, preprocessing the detected sub-image.
After the sub-images of the vehicle are obtained, the license plate needs to be detected in the sub-images, and the vehicle without the license plate is considered as a unlicensed vehicle. The detected sub-images are first pre-processed, including smoothing and stretching of the image, to remove the effects of noise and illumination, etc. This step is mainly prepared for the subsequent edge detection.
And 103, extracting the image edge of the preprocessed sub-image.
And (4) because the edge of the license plate area is obvious, vertical edge detection is carried out on the preprocessed image. Preferably, the detection can be performed by using a Sobel operator.
And 104, extracting the sub-image of the small block area near the edge point and extracting the color characteristic of the sub-image for the edge point.
And (3) carrying out binarization on the small block area subimage, namely setting the gray value of a pixel point of the small block area subimage to be 0 or 255, namely presenting the whole image with an obvious visual effect only of black and white. And respectively counting the color histogram of the corresponding point of the black area and the color histogram of the corresponding point of the white area after binarization, wherein the used color space is HSV color space, and combining the HSV color space and the HSV color space to obtain the color characteristics of the extraction block. The binarization algorithm makes the color features more distinctive.
And 105, judging by using a license plate color model, and detecting whether the extracted sub-image is a candidate license plate area.
And after the color features of the sub-images are extracted, judging by using a license plate color model, and detecting whether the sub-images are candidate license plate areas. The color model is divided into four types in the training phase: the method comprises the steps of carrying out binarization on a blue-bottom white license plate, a white-bottom black license plate, a black-bottom white license plate and a yellow-bottom black license plate, converting a color space from RGB to HSV, respectively counting histograms of points corresponding to a black-white area after binarization, combining the histograms to obtain the characteristics of each sample, and then training by using an SVM classifier. In the detection stage, as the SVM classifier returns a matching value, for each block of region, if the matching value is found to be larger through detection, the block of region is considered as a candidate license plate region, otherwise, the block of region is not the license plate region.
Step 106, detecting all candidate license plate areas meeting the conditions, finding the most matched area in all the candidate license plate areas, and determining the area as a license plate area;
and merging adjacent candidate license plate regions, judging the matching degree of the license plate through a color model, and considering the region with the highest matching degree as a real license plate region.
And step 107, if the license plate area is not detected, judging that the vehicle is a unlicensed vehicle.
In the embodiment of the invention, the license plate region is detected in a blocking way, the found boundary of the license plate region is inaccurate, and the upper, lower, left and right boundaries of the license plate are accurately positioned by using the color information.
According to the invention, the vehicle model is used for detecting the vehicle, and then the color model is used for judging the license plate, the color model is used for detecting the license plate, so that the clear license plate can be identified, the adaptability to the fuzzy license plate can be well realized, the identification rate of the license plate identification is improved, and the effect of detecting the license plate-free vehicle is good.
Fig. 2 is a schematic block diagram of a structure of a detecting device for a unlicensed vehicle according to an embodiment of the present invention. As shown in fig. 2, the apparatus includes: the device comprises a first detection unit, a processing unit, a first extraction unit, a second detection unit and a judgment unit. Wherein,
the first detection unit is used for detecting vehicles in the video and extracting sub-images of the vehicles in the video;
the processing unit is used for preprocessing the detected sub-images;
the first extraction unit is used for extracting the image edge of the preprocessed sub-image;
the second extraction unit is used for extracting the sub-image of the small block area near the edge point and extracting the color characteristic of the sub-image for the edge point;
the second detection unit is used for distinguishing by using the license plate color model and detecting whether the extracted sub-images are candidate license plate areas;
the judging unit is used for detecting all candidate license plate areas meeting the conditions, finding the most matched area in all the candidate license plate areas and determining the area as a license plate area; and if the license plate area is not detected, judging that the vehicle is a non-license vehicle.
According to the invention, the vehicle model is used for detecting the vehicle, and then the color model is used for judging the license plate, the color model is used for detecting the license plate, so that the clear license plate can be identified, the adaptability to the fuzzy license plate can be well realized, the identification rate of the license plate identification is improved, and the effect of detecting the license plate-free vehicle is good.
It will be obvious that many variations of the invention described herein are possible without departing from the true spirit and scope of the invention. Accordingly, all changes which would be obvious to one skilled in the art are intended to be included within the scope of this invention as defined by the appended claims. The scope of the invention is only limited by the claims.
Claims (10)
1. A method for detecting a unlicensed vehicle is characterized by comprising the following steps:
detecting vehicles in the video, and extracting vehicle sub-images in the video;
preprocessing the detected sub-images;
carrying out image edge extraction on the preprocessed sub-images;
for the edge point, extracting a small block area subimage near the edge point, and extracting the color characteristic of the subimage;
judging by using a license plate color model, and detecting whether the extracted sub-image is a candidate license plate area;
detecting all candidate license plate regions which meet the conditions, finding the most matched region in all the candidate license plate regions, and determining the region as a license plate region;
and if the license plate area is not detected, judging that the vehicle is a non-license vehicle.
2. The method of claim 1, wherein the step of detecting vehicles in the video and the step of extracting sub-images of vehicles in the video comprises:
detecting vehicles in the video through the vehicle model, and extracting vehicle sub-images in the video; the vehicle model is obtained by extracting a haar feature of a vehicle and then learning by using an Andubbs adaboost classifier, and the haar feature and the adaboost classifier are also used for detecting the vehicle in the video during detection.
3. The method of claim 1, wherein the pre-processing the detected sub-images comprises:
and smoothing and stretching the sub-images of the vehicle, and further eliminating the influence of illumination and noise.
4. The method of claim 1, wherein the step of extracting the image edge of the preprocessed sub-image comprises:
and performing vertical edge detection on the preprocessed sub-images by adopting a Sobel operator.
5. The method according to claim 1, wherein for the edge point, the extracting the sub-image of the small block area near the edge point and the extracting the color feature of the sub-image comprises:
and carrying out binarization on the sub-image of the small block region, respectively counting a color histogram of a corresponding point of a black region and a color histogram of a corresponding point of a white region after binarization, wherein the used color space is a Hue Saturation Value (HSV) color space, and combining the hue saturation value and the HSV color space to obtain the color characteristics of the extraction block.
6. The method of claim 1, wherein the step of discriminating using the license plate color model and detecting whether the extracted sub-image is a candidate license plate region comprises:
and judging whether the sub-image of the current small area is the license plate area or not according to the trained license plate color model.
7. The method of claim 6, wherein the color models are grouped into four classes in the training phase: carrying out binarization on samples, converting a color space from RGB to HSV, respectively counting histograms of points corresponding to a black-white area after binarization, combining the histograms to obtain the characteristics of each sample, and then training by using a Support Vector Machine (SVM) classifier; in the detection stage, as the SVM classifier returns a matching value, for each block of region, if the matching value is found to be larger through detection, the block of region is considered as a candidate license plate region, otherwise, the block of region is not the candidate license plate region.
8. The method of claim 1, wherein the step of detecting all candidate license plate regions that meet the conditions and finding the best matching region among all candidate license plate regions to determine the license plate region comprises:
and merging adjacent candidate license plate regions, judging the matching degree of the license plate through a color model, and considering the region with the highest matching degree as a real license plate region.
9. A unlicensed vehicle detection device, comprising:
the first detection unit is used for detecting vehicles in the video and extracting sub-images of the vehicles in the video;
the processing unit is used for preprocessing the detected sub-images;
the first extraction unit is used for extracting the image edge of the preprocessed sub-image;
the second extraction unit is used for extracting the sub-image of the small block area near the edge point and extracting the color characteristic of the sub-image for the edge point;
the second detection unit is used for distinguishing by using the license plate color model and detecting whether the extracted sub-images are candidate license plate areas;
the judging unit is used for detecting all candidate license plate areas meeting the conditions, finding the most matched area in all the candidate license plate areas and determining the area as a license plate area; and if the license plate area is not detected, judging that the vehicle is a non-license vehicle.
10. The apparatus according to claim 9, wherein the first detection unit is specifically configured to:
detecting vehicles in the video through the vehicle model, and extracting vehicle sub-images in the video; the vehicle model is obtained by extracting haar features of a vehicle and then learning by using an adaboost classifier, and the haar features and the adaboost classifier are used for detecting the vehicle in the video during detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510850001.XA CN105512662A (en) | 2015-06-12 | 2015-11-29 | Detection method and apparatus for unlicensed vehicle |
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2015103258575 | 2015-06-12 | ||
| CN201510325857 | 2015-06-12 | ||
| CN201510850001.XA CN105512662A (en) | 2015-06-12 | 2015-11-29 | Detection method and apparatus for unlicensed vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105512662A true CN105512662A (en) | 2016-04-20 |
Family
ID=55720629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510850001.XA Pending CN105512662A (en) | 2015-06-12 | 2015-11-29 | Detection method and apparatus for unlicensed vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105512662A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203422A (en) * | 2016-06-28 | 2016-12-07 | 北京智芯原动科技有限公司 | License plate shading detection method based on hsv color space and device |
| CN106845341A (en) * | 2016-12-15 | 2017-06-13 | 南京积图网络科技有限公司 | A kind of unlicensed vehicle identification method based on virtual number plate |
| CN107918941A (en) * | 2017-11-01 | 2018-04-17 | 国网山东省电力公司电力科学研究院 | A kind of visualizing monitor system and method for broken protection outside passway for transmitting electricity |
| CN107977596A (en) * | 2016-10-25 | 2018-05-01 | 杭州海康威视数字技术股份有限公司 | A kind of car plate state identification method and device |
| CN113158758A (en) * | 2021-02-07 | 2021-07-23 | 中国联合网络通信集团有限公司 | Method, system, equipment and storage medium for judging illegal use of vehicle license plate |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130182910A1 (en) * | 2012-01-18 | 2013-07-18 | Xerox Corporation | License plate optical character recognition method and system |
| US20130272579A1 (en) * | 2012-04-17 | 2013-10-17 | Xerox Corporation | Robust cropping of license plate images |
| CN103514751A (en) * | 2012-06-19 | 2014-01-15 | 广州市捷众科贸有限公司 | Vehicle information identification apparatus |
| CN103530640A (en) * | 2013-11-07 | 2014-01-22 | 沈阳聚德视频技术有限公司 | Unlicensed vehicle detection method based on AdaBoost and SVM (support vector machine) |
| CN104050450A (en) * | 2014-06-16 | 2014-09-17 | 西安通瑞新材料开发有限公司 | Vehicle license plate recognition method based on video |
| US20140369566A1 (en) * | 2006-04-04 | 2014-12-18 | Cyclops Technologies, Inc. | Perimeter Image Capture and Recognition System |
| CN104463170A (en) * | 2014-12-04 | 2015-03-25 | 江南大学 | Unlicensed vehicle detecting method based on multiple detection under gate system |
| CN104537841A (en) * | 2014-12-23 | 2015-04-22 | 上海博康智能信息技术有限公司 | Unlicensed vehicle violation detection method and detection system thereof |
| CN104616381A (en) * | 2015-01-28 | 2015-05-13 | 苏州市职业大学 | Intelligent measuring and controlling access control system for automobile passage of community estate |
-
2015
- 2015-11-29 CN CN201510850001.XA patent/CN105512662A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140369566A1 (en) * | 2006-04-04 | 2014-12-18 | Cyclops Technologies, Inc. | Perimeter Image Capture and Recognition System |
| US20130182910A1 (en) * | 2012-01-18 | 2013-07-18 | Xerox Corporation | License plate optical character recognition method and system |
| US20130272579A1 (en) * | 2012-04-17 | 2013-10-17 | Xerox Corporation | Robust cropping of license plate images |
| CN103514751A (en) * | 2012-06-19 | 2014-01-15 | 广州市捷众科贸有限公司 | Vehicle information identification apparatus |
| CN103530640A (en) * | 2013-11-07 | 2014-01-22 | 沈阳聚德视频技术有限公司 | Unlicensed vehicle detection method based on AdaBoost and SVM (support vector machine) |
| CN104050450A (en) * | 2014-06-16 | 2014-09-17 | 西安通瑞新材料开发有限公司 | Vehicle license plate recognition method based on video |
| CN104463170A (en) * | 2014-12-04 | 2015-03-25 | 江南大学 | Unlicensed vehicle detecting method based on multiple detection under gate system |
| CN104537841A (en) * | 2014-12-23 | 2015-04-22 | 上海博康智能信息技术有限公司 | Unlicensed vehicle violation detection method and detection system thereof |
| CN104616381A (en) * | 2015-01-28 | 2015-05-13 | 苏州市职业大学 | Intelligent measuring and controlling access control system for automobile passage of community estate |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203422A (en) * | 2016-06-28 | 2016-12-07 | 北京智芯原动科技有限公司 | License plate shading detection method based on hsv color space and device |
| CN106203422B (en) * | 2016-06-28 | 2019-05-07 | 北京智芯原动科技有限公司 | License plate shading detection method and device based on hsv color space |
| CN107977596A (en) * | 2016-10-25 | 2018-05-01 | 杭州海康威视数字技术股份有限公司 | A kind of car plate state identification method and device |
| CN106845341A (en) * | 2016-12-15 | 2017-06-13 | 南京积图网络科技有限公司 | A kind of unlicensed vehicle identification method based on virtual number plate |
| CN106845341B (en) * | 2016-12-15 | 2020-04-10 | 南京积图网络科技有限公司 | Unlicensed vehicle identification method based on virtual number plate |
| CN107918941A (en) * | 2017-11-01 | 2018-04-17 | 国网山东省电力公司电力科学研究院 | A kind of visualizing monitor system and method for broken protection outside passway for transmitting electricity |
| CN113158758A (en) * | 2021-02-07 | 2021-07-23 | 中国联合网络通信集团有限公司 | Method, system, equipment and storage medium for judging illegal use of vehicle license plate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993056B (en) | Method, server and storage medium for identifying vehicle illegal behaviors | |
| CN108364010B (en) | License plate recognition method, device, equipment and computer readable storage medium | |
| CN109740478B (en) | Vehicle detection and identification method, device, computer equipment and readable storage medium | |
| CN107301405A (en) | Method for traffic sign detection under natural scene | |
| CN111382704A (en) | Vehicle line-pressing violation judgment method and device based on deep learning and storage medium | |
| CN106650553A (en) | License plate recognition method and system | |
| Sulaiman et al. | Development of automatic vehicle plate detection system | |
| CN104050684B (en) | A kind of video frequency motion target sorting technique based on on-line training and system | |
| CN105512662A (en) | Detection method and apparatus for unlicensed vehicle | |
| CN110991221B (en) | Dynamic traffic red light running recognition method based on deep learning | |
| CN106203237A (en) | The recognition methods of container-trailer numbering and device | |
| Antar et al. | Automatic number plate recognition of Saudi license car plates | |
| CN105184291B (en) | A kind of polymorphic type detection method of license plate and system | |
| Azad et al. | New method for optimization of license plate recognition system with use of edge detection and connected component | |
| CN105787475A (en) | Traffic sign detection and identification method under complex environment | |
| CN103699876B (en) | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images | |
| CN111178359A (en) | License plate number recognition method, device and equipment and computer storage medium | |
| CN107392115A (en) | A kind of traffic sign recognition method based on layered characteristic extraction | |
| CN117523521B (en) | Vehicle detection method based on Haar features and improved HOG features | |
| CN102129569A (en) | Equipment and method for detecting object based on multiscale comparison characteristic | |
| Satish et al. | Edge assisted fast binarization scheme for improved vehicle license plate recognition | |
| CN107506777A (en) | A kind of real-time more licence plate recognition methods and device based on Wavelet transformation and SVMs | |
| He et al. | Combining global and local features for detection of license plates in video | |
| KR20190143525A (en) | A Method of Detecting Character Data through a Adaboost Learning Method | |
| Angeline et al. | Tracking and localisation of moving vehicle license plate via Signature Analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160420 |