CN103646544A - Vehicle-behavior analysis and identification method based on holder and camera device - Google Patents
Vehicle-behavior analysis and identification method based on holder and camera device Download PDFInfo
- Publication number
- CN103646544A CN103646544A CN201310567228.4A CN201310567228A CN103646544A CN 103646544 A CN103646544 A CN 103646544A CN 201310567228 A CN201310567228 A CN 201310567228A CN 103646544 A CN103646544 A CN 103646544A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- cloud terrace
- target
- holder
- 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)
- Studio Devices (AREA)
Abstract
The invention discloses a vehicle-behavior analysis and identification method based on a holder and a camera device. The method includes the following steps: performing movement foreground detection through a mixed Gaussian background modeling method based on image weak edges; detecting movement foreground areas through use of a vehicle detection algorithm based on cascaded LBP space histogram features and judging whether vehicles are available in the areas and locating the positions of the vehicles accurately; performing matching and locating a target vehicle for a long time through use of a rapid vehicle matching algorithm based on class-Fern features; judging whether the target vehicle is illegally parked through use of the number of matched features of the target and after a preset position of the holder is switched, analyzing and identifying a before-event target vehicle; and realizing all functions of acquisition of real-time video images, vehicle-behavior analysis, holder linkage, image compression and network transmission and the like through use of an insert-type integral hardware structure. Device management roles of enabling according to time periods and enabling according to preset positions are also played. Rear-end platform software is only needed to receive pictures and to execute data compilation and selection work.
Description
Technical field
The invention belongs to intelligent transport technology field, relate to a kind of vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus.
Background technology
In intelligent transportation industry, CCTV camera and The Cloud Terrace are very universal, but lower to the intelligent degree of the behavior determination and analysis of vehicle, automatically detect event (parking offense violating the regulations, drive in the wrong direction etc.) indifferent, mostly send special messenger to check, so not only need to drop into a large amount of human and material resources, and because people's energy and notice are limited, under high-intensity working environment, tending to occur careless omission, thereby, can not to abnormal conditions, react in time.
Summary of the invention
The present invention is exactly in order to solve above-mentioned the problems of the prior art, and a kind of vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus is provided.
In order to achieve the above object, the present invention adopts following technical scheme:
Vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus of the present invention, comprises the steps:
Utilization based on image a little less than the mixed Gaussian background modeling method at edge carry out sport foreground detection;
Utilization is based on cascade LBP(local binary patterns, local binary patterns feature) vehicle detecting algorithm of spatial histogram feature detects sport foreground region, judges whether this region has vehicle, and accurate positioned vehicle position;
The rapid vehicle matching algorithm of utilization based on class fern (Fern) feature mates localizing objects vehicle for a long time;
Utilize clarification of objective number of matches to determine whether parking offense, after cradle head preset positions switches, do not detecting Static Detection target vehicle under sport foreground, target vehicle is in advance analyzed and identified;
Use embedded integrated hardware configuration, realize collection, vehicle behavioural analysis, The Cloud Terrace interlock, the focusing of camera zoom, vehicle snapshot, car plate identification, compression of images and the Internet Transmission of real time video image.
Wherein, utilizing mixed Gaussian background modeling method based on edge a little less than image to carry out the concrete steps of sport foreground detection as follows: first to utilize improved large scale SOBEL(Sobel) operator carries out vertical and horizontal direction convolution and gets maximal value obtaining outline map to image; Then with Image boundaries, set up mixed Gauss model and set up background and extraction prospect.
The vehicle detecting algorithm of utilization based on cascade LBP spatial histogram feature confirm to detect in sport foreground, whether have automobile storage step cascade used two kinds of sorters: fast detecting also filters out the SVM(support vector machine of non-vehicle, support vector base) linear classifier and the SVM HIK(Histogram intersection kernel that carries out accurate confirmation, histogram intersection core) Nonlinear Classifier.
Rapid vehicle matching algorithm based on class Fern feature is divided into subregion matching image, utilizes integrogram method to calculate average gray in all subregions as matching criterior.
Utilize clarification of objective number of matches to determine whether parking offense, every frame image is detected to position, the size of moving target and constantly upgrades apart from the buffer zone of putting into regular length, and the up-to-date target signature detecting and historical data traversal are mated to numeration, reach predetermined value just for stopping.
After cradle head preset positions switches, adopt the static vehicle detection technology based on many demarcation yardstick, target vehicle is in advance analyzed and identified, draw near and calculate different vehicle calibration yardsticks.
Use embedded integrated hardware configuration, by four modules such as intelligent analysis module, video acquisition buffer module, The Cloud Terrace main control module and video compress, at The Cloud Terrace front end, complete monitoring, intellectual analysis function.
Advantage and good effect that the present invention has are:
Vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus of the present invention, can carry out real-time detection and analysis to target vehicle, vehicles peccancy is captured to image video recording, record whole process violating the regulations, operating personnel only need to inquire about record violating the regulations, have greatly improved operating personnel's work efficiency.The method can be reacted and record abnormal conditions in time, has avoided owing to manually causing careless omission.
Accompanying drawing explanation
Fig. 1 is the computing method of LBP operator of the present invention;
Fig. 2 is LBP spatial histogram of the present invention;
Fig. 3 is the vehicle detecting algorithm process flow diagram based on cascade LBP spatial histogram feature;
Fig. 4 is the block plan of the rapid vehicle matching algorithm based on class Fern feature;
Fig. 5 is system hardware architecture block diagram of the present invention;
Fig. 6 is the process flow diagram of vehicles peccancy detection, vehicle snapshot, car plate analysis identification.
Embodiment
Below in conjunction with the drawings and specific embodiments, the vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus of the present invention is described further.Following each embodiment is not only limitation of the present invention for the present invention is described.
Vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus of the present invention, comprises the steps:
Utilization based on image a little less than the mixed Gaussian background modeling method at edge carry out sport foreground detection:
The vehicle detecting algorithm of utilization based on cascade LBP spatial histogram feature detects sport foreground region, judges whether this region has vehicle, and accurate positioned vehicle position;
The rapid vehicle matching algorithm of utilization based on class Fern feature mates localizing objects vehicle for a long time;
Utilize clarification of objective number of matches to determine whether parking offense, after cradle head preset positions switches, do not detecting Static Detection target vehicle under sport foreground, target vehicle is in advance analyzed and identified;
Use embedded integrated hardware configuration, realize the repertoires such as collection, vehicle behavioural analysis, The Cloud Terrace interlock, the focusing of camera zoom, vehicle snapshot, car plate identification, compression of images and Internet Transmission of real time video image, also there is the equipment Management Functions such as time segment enables, a minute presetting bit enables simultaneously.
Wherein, utilization based on image a little less than the mixed Gaussian background modeling method at edge to carry out the concrete steps of sport foreground detection as follows: first utilize improved large scale SOBEL operator to carry out vertical and horizontal direction convolution and get maximal value obtaining outline map to image, can make more weak edge strengthen, then with Image boundaries, set up mixed Gauss model and set up background and extraction prospect, the illegal vehicle that sails setting regions into be can extract fast, the anti-interference of system and the accuracy of detection greatly improved.
Whether the vehicle detecting algorithm of utilization based on cascade LBP spatial histogram feature confirmed to detect in sport foreground has automobile storage to exist, SVM linear classifier and two kinds of sorters of SVM HIK Nonlinear Classifier have been used in this step cascade, linear classifier fast detecting also filters out non-vehicle, and Nonlinear Classifier is confirmed accurately.
The computing method of LBP operator as shown in Figure 1, for each pixel as central point and the pixel in 8 UNICOM territories around, compare, if be greater than or equal to, what obtain corresponding position is encoded to 1, otherwise be 0, the coding of these 8 corresponding positions coupled together to the decimal representation that obtains 8 bits in a certain order and be the LBP value of this central point pixel.
LBP spatial histogram as shown in Figure 2, vehicle sample is divided into certain cell, every 2x2 cell is designated as a block, in each block, add up LBP histogram, each block in the horizontal direction, the stepping that vertical direction moves is a cell, until travel through whole sample image, and the histogram of each block is together in series and obtains the LBP spatial histogram feature of whole sample.
Vehicle detecting algorithm process flow diagram based on cascade LBP spatial histogram feature as shown in Figure 3.Foreground image is extracted to LBP spatial histogram feature, each feature is utilized respectively to the judgement of classifying of two sorters, all think and have car to think that there is car this position, otherwise think that this position is without car.
Rapid vehicle matching algorithm based on class Fern feature can mate target vehicle for a long time, this algorithm is divided into subregion matching image, utilize integrogram method to calculate average gray in all subregions as matching criterior, this algorithm travelling speed is fast, to blocking with illumination variation, has certain robustness.
Rapid vehicle matching algorithm based on class Fern feature is divided into 13 sub regions matching image, as shown in Figure 4, add up respectively subregion average mate.
Utilize clarification of objective number of matches to determine whether parking offense, every frame image is detected to position, the size of moving target and constantly upgrades apart from the buffer zone of putting into regular length, and the up-to-date target signature detecting and historical data traversal are mated to numeration, reach predetermined value and just think parking, all parameters are adjustable, greatly improved the adaptability of system.
After cradle head preset positions switches, adopt the static vehicle detection technology based on many demarcation yardstick, can target vehicle in advance be analyzed and be identified.This technology is demarcated yardstick to vehicle detection and is carried out logic optimization, draw near and calculate different vehicle calibration yardsticks, different vehicles far and near, different sizes in scene all can accurately be detected by the vehicle detecting algorithm based on cascade LBP spatial histogram feature.
Use embedded integrated hardware configuration, as shown in Figure 5, hardware circuit mainly comprises intellectual analysis main control module, video acquisition buffer module, The Cloud Terrace main control module and video compressing module.By intelligent analysis module, video acquisition buffer module, The Cloud Terrace main control module and video compressing module, can complete monitoring, intellectual analysis function at The Cloud Terrace front end, this system has fast response time, takies rear end platform resource few, and intellectual analysis is without advantages such as time delays.
At The Cloud Terrace front end, realize the repertoires such as collection, vehicle behavioural analysis, The Cloud Terrace interlock, the focusing of camera zoom, vehicle snapshot, car plate identification, compression of images and Internet Transmission of video image, also have the equipment Management Functions such as time segment enables, a minute presetting bit enables, rear end platform software is as long as receive picture and do data preparation screening operation simultaneously.
Vehicles peccancy detection, vehicle snapshot, car plate identification thread realization flow figure are as shown in Figure 6, when having vehicles peccancy, need to capture panorama sketch, calculate parking duration, surpass after regulation duration, control The Cloud Terrace, capture feature, carry out car plate identification, then control The Cloud Terrace, return to monitoring position, again capture panoramic pictures.
Claims (7)
1. the vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus, is characterized in that, the method comprises the steps:
Utilization based on image a little less than the mixed Gaussian background modeling method at edge carry out sport foreground detection;
The vehicle detecting algorithm of the LBP spatial histogram feature of utilization based on cascade detects sport foreground region, judges whether this region has vehicle, and accurate positioned vehicle position;
The rapid vehicle matching algorithm of utilization based on class fern feature mates localizing objects vehicle for a long time;
Utilize clarification of objective number of matches to determine whether parking offense, after cradle head preset positions switches, do not detecting Static Detection target vehicle under sport foreground, target vehicle is in advance analyzed and identified;
Use embedded integrated hardware configuration, realize collection, vehicle behavioural analysis, The Cloud Terrace interlock, the focusing of camera zoom, vehicle snapshot, car plate identification, compression of images and the Internet Transmission of real time video image.
2. the vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus according to claim 1, it is characterized in that, utilize mixed Gaussian background modeling method based on edge a little less than image to carry out the concrete steps of sport foreground detection as follows: first utilize improved large scale SOBEL operator to carry out vertical and horizontal direction convolution and get maximal value obtaining outline map to image; Then with Image boundaries, set up mixed Gauss model and set up background and extraction prospect.
3. the vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus according to claim 1, it is characterized in that, utilize vehicle detecting algorithm based on cascade LBP spatial histogram feature to confirm to detect whether to have in sport foreground automobile storage step cascade used two kinds of sorters: fast detecting also filters out the SVM linear classifier of non-vehicle and carries out the accurate Nonlinear Classifier based on SVM HIK of confirming.
4. the vehicle behavioural analysis recognition methods based on The Cloud Terrace and camera apparatus according to claim 1, it is characterized in that, rapid vehicle matching algorithm based on class Fern feature is divided into subregion matching image, utilizes integrogram method to calculate average gray in all subregions as matching criterior.
5. according to claim 1 based on Switching Power Supply infrared lamp driving circuit, it is characterized in that: utilize clarification of objective number of matches to determine whether parking offense, every frame image is detected to position, the size of moving target and constantly upgrades apart from the buffer zone of putting into regular length, and the up-to-date target signature detecting and historical data traversal are mated to numeration, reach predetermined value just for stopping.
6. according to claim 1 based on Switching Power Supply infrared lamp driving circuit, it is characterized in that: after cradle head preset positions switches, the static vehicle detection technology of employing based on many demarcation yardstick, analyzes and identification target vehicle in advance, draws near and calculates different vehicle calibration yardsticks.
7. according to claim 1 based on Switching Power Supply infrared lamp driving circuit, it is characterized in that: use embedded integrated hardware configuration, by four modules such as intelligent analysis module, video acquisition buffer module, The Cloud Terrace main control module and video compress, at The Cloud Terrace front end, complete monitoring, intellectual analysis function.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310567228.4A CN103646544B (en) | 2013-11-15 | 2013-11-15 | Based on the vehicle behavioural analysis recognition methods of The Cloud Terrace and camera apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310567228.4A CN103646544B (en) | 2013-11-15 | 2013-11-15 | Based on the vehicle behavioural analysis recognition methods of The Cloud Terrace and camera apparatus |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103646544A true CN103646544A (en) | 2014-03-19 |
CN103646544B CN103646544B (en) | 2016-03-09 |
Family
ID=50251750
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310567228.4A Active CN103646544B (en) | 2013-11-15 | 2013-11-15 | Based on the vehicle behavioural analysis recognition methods of The Cloud Terrace and camera apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103646544B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104157143A (en) * | 2014-08-15 | 2014-11-19 | 青岛比特信息技术有限公司 | Illegal parking detection system and detection method thereof |
CN104778842A (en) * | 2015-04-29 | 2015-07-15 | 深圳市保千里电子有限公司 | Cloud vehicle running track tracing method and system based on vehicle license plate recognition |
CN106446892A (en) * | 2016-09-13 | 2017-02-22 | 东软集团股份有限公司 | Vehicle license plate recognizing method, apparatus and charging pile |
CN106878674A (en) * | 2017-01-10 | 2017-06-20 | 哈尔滨工业大学深圳研究生院 | A kind of parking detection method and device based on monitor video |
CN109035805A (en) * | 2018-09-21 | 2018-12-18 | 深圳市九洲电器有限公司 | A kind of intelligent identification Method and device of license plate number |
CN111291748A (en) * | 2020-01-15 | 2020-06-16 | 广州玖峰信息科技有限公司 | Cascade distributed artificial intelligence case number identification system |
CN112183350A (en) * | 2020-09-28 | 2021-01-05 | 天地伟业技术有限公司 | Video-based illegal parking detection method |
CN113592943A (en) * | 2020-04-30 | 2021-11-02 | 丰田自动车株式会社 | Position estimation system and position estimation method |
Citations (6)
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 |
CN101183427A (en) * | 2007-12-05 | 2008-05-21 | 浙江工业大学 | Computer vision based peccancy parking detector |
EP1978470A1 (en) * | 2007-04-05 | 2008-10-08 | Mitsubishi Electric Corporation | Method for detecting objects left-behind in a scene |
JP2012038318A (en) * | 2010-08-10 | 2012-02-23 | Fujitsu Ltd | Target detection method and device |
CN102637257A (en) * | 2012-03-22 | 2012-08-15 | 北京尚易德科技有限公司 | Video-based detection and recognition system and method of vehicles |
CN103035013A (en) * | 2013-01-08 | 2013-04-10 | 东北师范大学 | Accurate moving shadow detection method based on multi-feature fusion |
-
2013
- 2013-11-15 CN CN201310567228.4A patent/CN103646544B/en active Active
Patent Citations (6)
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 |
EP1978470A1 (en) * | 2007-04-05 | 2008-10-08 | Mitsubishi Electric Corporation | Method for detecting objects left-behind in a scene |
CN101183427A (en) * | 2007-12-05 | 2008-05-21 | 浙江工业大学 | Computer vision based peccancy parking detector |
JP2012038318A (en) * | 2010-08-10 | 2012-02-23 | Fujitsu Ltd | Target detection method and device |
CN102637257A (en) * | 2012-03-22 | 2012-08-15 | 北京尚易德科技有限公司 | Video-based detection and recognition system and method of vehicles |
CN103035013A (en) * | 2013-01-08 | 2013-04-10 | 东北师范大学 | Accurate moving shadow detection method based on multi-feature fusion |
Non-Patent Citations (1)
Title |
---|
郝士新: "基于视频的运动车辆检测和跟踪算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑 》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104157143A (en) * | 2014-08-15 | 2014-11-19 | 青岛比特信息技术有限公司 | Illegal parking detection system and detection method thereof |
CN104778842A (en) * | 2015-04-29 | 2015-07-15 | 深圳市保千里电子有限公司 | Cloud vehicle running track tracing method and system based on vehicle license plate recognition |
CN106446892A (en) * | 2016-09-13 | 2017-02-22 | 东软集团股份有限公司 | Vehicle license plate recognizing method, apparatus and charging pile |
CN106878674A (en) * | 2017-01-10 | 2017-06-20 | 哈尔滨工业大学深圳研究生院 | A kind of parking detection method and device based on monitor video |
CN106878674B (en) * | 2017-01-10 | 2019-08-30 | 哈尔滨工业大学深圳研究生院 | A kind of parking detection method and device based on monitor video |
CN109035805A (en) * | 2018-09-21 | 2018-12-18 | 深圳市九洲电器有限公司 | A kind of intelligent identification Method and device of license plate number |
CN109035805B (en) * | 2018-09-21 | 2021-03-02 | 深圳市九洲电器有限公司 | Intelligent recognition method and device for license plate number |
CN111291748A (en) * | 2020-01-15 | 2020-06-16 | 广州玖峰信息科技有限公司 | Cascade distributed artificial intelligence case number identification system |
CN113592943A (en) * | 2020-04-30 | 2021-11-02 | 丰田自动车株式会社 | Position estimation system and position estimation method |
CN113592943B (en) * | 2020-04-30 | 2024-01-30 | 丰田自动车株式会社 | Position estimation system and position estimation method |
CN112183350A (en) * | 2020-09-28 | 2021-01-05 | 天地伟业技术有限公司 | Video-based illegal parking detection method |
CN112183350B (en) * | 2020-09-28 | 2023-07-14 | 天地伟业技术有限公司 | Video-based illegal parking detection method |
Also Published As
Publication number | Publication date |
---|---|
CN103646544B (en) | 2016-03-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103646544B (en) | Based on the vehicle behavioural analysis recognition methods of The Cloud Terrace and camera apparatus | |
Asha et al. | Vehicle counting for traffic management system using YOLO and correlation filter | |
CN103824066B (en) | A kind of licence plate recognition method based on video flowing | |
CN103093249B (en) | A kind of taxi identification method based on HD video and system | |
CN104751634B (en) | The integrated application method of freeway tunnel driving image acquisition information | |
CN103077407B (en) | Car logo positioning and recognition method and car logo positioning and recognition system | |
CN102759347B (en) | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof | |
CN106571039A (en) | Automatic snapshot system for highway traffic offence | |
CN103093201B (en) | Vehicle-logo location recognition methods and system | |
CN101231786A (en) | Vehicle checking method based on video image characteristic | |
CN108269407B (en) | Security robot capable of automatically managing people stream and logistics | |
CN104050679A (en) | Illegal parking automatic evidence obtaining method | |
CN103927878A (en) | Automatic snapshot device and method for illegal parking | |
CN105574543A (en) | Vehicle brand and model identifying method and system based on deep learning | |
CN103605953A (en) | Vehicle interest target detection method based on sliding window search | |
CN103279756A (en) | Vehicle detecting analysis system and detecting analysis method thereof based on integrated classifier | |
CN104537360A (en) | Method and system for detecting vehicle violation of not giving way | |
CN101937614A (en) | Plug and play comprehensive traffic detection system | |
CN106991821A (en) | Vehicles peccancy hand-held mobile terminal data collecting system | |
CN104378539A (en) | Scene-adaptive video structuring semantic extraction camera and method thereof | |
CN102307297A (en) | Intelligent monitoring system for multi-azimuth tracking and detecting on video object | |
Jensen et al. | Presenting the multi-view traffic intersection dataset (MTID): A detailed traffic-surveillance dataset | |
CN204375161U (en) | Parking offense automatic snapshot system | |
CN102682606A (en) | Vehicle recognizing system and vehicle recognizing method | |
Jie et al. | Computer vision based real-time information acquisition for transport traffic |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | 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 | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: 300384 Tianjin City Huayuan Industrial Zone (outer ring road No. 8) two Haitai branch Patentee after: Tiandi Weiye Technology Co., Ltd. Address before: 300384 Tianjin city Xiqing District Huayuan new technology Industrial Park (outer ring road No. 8) two Haitai branch Patentee before: Tianjin Tiandy Digital Technology Co., Ltd. |