CN103778785A - Vehicle tracking and detecting method based on parking lot environment video monitoring - Google Patents
Vehicle tracking and detecting method based on parking lot environment video monitoring Download PDFInfo
- Publication number
- CN103778785A CN103778785A CN201210403965.6A CN201210403965A CN103778785A CN 103778785 A CN103778785 A CN 103778785A CN 201210403965 A CN201210403965 A CN 201210403965A CN 103778785 A CN103778785 A CN 103778785A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target
- background
- parking lot
- tracking
- 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
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle tracking and detecting method based on parking lot environment video monitoring and relates to the field of pattern identification, detection and tracking of a moving object and the problem of video monitoring. Through the method of the invention, the monitoring problems of the parking lot environment are obtained more accurately, and compared with the conventional human monitoring method, the method of the invention has the feature of real-time non-interrupted monitoring; and by introducing and using the algorithm of pattern identification, and through the modes of vehicle object detection and correlation analysis of each frame image within time period and the like, the object state of a vehicle is obtained, furthermore, the environment state of a parking lot is obtained, and thus the problem of intelligent monitoring of the parking lot environment is solved.
Description
Technical field
The present invention relates to area of pattern recognition, especially a kind of vehicle tracking and detection method based on parking lot circumstance video monitoring.
Background technology
At present, the detection of moving target and tracking have become a major issue of computer vision field.It has merged many-sided knowledge such as image processing, pattern-recognition, artificial intelligence, and in producing and living, has application very widely.Detection in conjunction with the parking lot vehicle of video monitoring is a kind of important means of parking lot environmental monitoring with following the tracks of.Because the video monitoring employing personnel in actual parking lot monitor screen, therefore, the in the situation that of less in control point, monitoring effect is better.
Inventor is realizing in process of the present invention, finds at least to exist in prior art following shortcoming and defect:
The manual supervisory means of the many employings of prior art, in the time that control point is more, monitor staff cannot be comprehensive, complete all information of monitoring, and the entering of vehicle, walking path and the various states such as leave, cannot carry out the status information of obtaining and mark in real time vehicle of intelligence, and the automatic statistics of state, warn, thereby carry out the management in parking lot.(whether have the technology of some laser rangings, the technology of laser ranging is directly perceived not)
Summary of the invention
The invention provides a kind of vehicle tracking and detection method based on parking lot circumstance video monitoring, the video information that the present invention obtains according to watch-dog, vehicle in video is detected, and follow the tracks of its operating path, obtain the status information of vehicle, and information is shown to statistics is to relevant managerial personnel, reach the object of parking lot environment being carried out to intelligent monitoring, the performance that has improved monitoring, has reduced manpower cost, described below:
Vehicle tracking based on parking lot circumstance video monitoring and a detection method, comprising: the detection of vehicle in video, and the tracking in vehicle operating path, the acquisition of vehicle-state.Vehicle checking method in described video, comprises the vehicle checking method of improvement background subtraction separating method and the structure update strategy of background that the threshold value based on RGB color space is divided, and obtains the morphology noise reduction process detecting after target.The tracking of the target of described vehicle, vehicle-state obtains and comprises, vehicle behavioural analysis and vehicle tracking and event handling.
Described background constructing update strategy comprises: the update strategy of initial background structure and background.
Described morphology denoising comprises: based on corrosion and the basic denoising of expanding and the combination denoising based on ' open and close '.
The behavioural analysis of described vehicle comprises: the definition of vehicle target state, state conversion and event definition.
Tracking and the event handling of described vehicle comprise: the extraction based on motion feature and matching process are determined the region of target travel, the processing of the judgement of vehicle-state and vehicle behavior event.
Said method comprising the steps of:
(1) described in, improve one's methods and on described video, extract reliable background, and detect vehicle based on described improvement background subtraction separating method.
(2) described background subtraction point-score obtains target vehicle morphology denoising afterwards.
(3) the vehicle target profile of drawing described background subtraction separating method acquisition on described video is so that tracking target.
(4) behavior that the relevance between the each frame of described video, registration analysis obtain vehicle statistics feedback
The reliable background extracting method of described acquisition is specially: the present invention adopts the context update strategy of real-time adjustment, to reduce the impact of the result that the variation of motion or illumination condition etc. of background object wipes out for background.Described context update strategy comprises the structure of background and two steps of the renewal of background.The present invention adopts initial photographic images as initial background, and carries out on this basis the renewal of background.Described background update method kind is replaced old background pixel value to upgrade background with new background pixel value.Even judge that current certain pixel is background area, uses corresponding point in this pixel replacement background; Otherwise, still keep original value.The video frame images that defines current input is Fn, the old background image that Bn-1 obtains before being.The present frame pixel corresponding with background frames subtracted each other and obtain the difference value Dn (x of this some place, y): Dn (x, y)=| Fn (x, y)-Bn-1 (x, y) | suppose to use threshold value Th to divide pixel, Dn is greater than the foreground point of thinking of threshold value, does not upgrade background, otherwise replaces old background value.
Described improvement background subtraction separating method is specially: the present invention adopts the threshold value division methods based on RGB color space to improve background difference algorithm and is converted into overcome colored video image in the process of gray level image, can cause the loss of colouring information, or select the gray level image after conversion to carry out difference operation, be difficult to the problem of the interference that overcomes gray scale similarity.F (x, y) is a pixel of present frame Fn, and the pixel value of its R, G, tri-passages of B is respectively Fr (x, y), Fg (x, y), Fb (x, y).The triple channel value Br (x with corresponding background pixel point by these three pixel values respectively, y), Bg (x, y), Bb (x, y) subtracts each other, and obtains difference value Dr (x, y), Dg (x, y), Db (x, y) then obtains average D (x, y) to three difference values, judge thus the similarity degree of current pixel point and background pixel point, carry out threshold decision.Choose new threshold value Th ', and on this basis the pixel F in two field picture is carried out to two-value division, obtain result R.
The morphology noise reduction process of described vehicle target is specially: adopt morphologic image processing method by it removal.The common morphological operation for noise reduction process is that burn into expands, open and close.Open and close computing is the combination that burn into expands.Solve video in continuous shooting process, there will be the problem such as flicker or reflection of light, and then contain some noises among a small circle in the result that thresholding processing is obtained.
Described vehicle target profile preparation method is specially: the present invention adopts the power function that OpenCV provides to find target external outline line according to binary image, then draws out the boundary rectangle that can surround profile according to this group outline line.According to the origin of this extraneous rectangle, height and width, can further determine the barycenter of target.The coupling of position feature is mainly judged by the coincidence degree of boundary rectangle.R1 (x1, y1, w1, h1), R2 (x2, y2, w2, h2) is two rectangles, its parameter is respectively upper left corner starting point x, the y left side, rectangle width and height, and the area of R1, R2 is respectively S1, S2.Rectangle R3 (x3, y3, w3, h3) is the intersection of R1 and R2, and area is S3.Define rectangle R1 as follows with respect to the coincidence factor CR (coincide rate) of R2: CR=S3/S1.Two boundary rectangles that adjacent two interframe coincidence factors are very high, can think the diverse location of same target two moment.
Described vehicle behavior analysis method is specially: the Main Basis of analyzing vehicle target state variation is that the change in location rule of target in whole active procedure is by target location incidence matrix between definition frame, and cover correlation analysis and determine the method for dbjective state by position, analyze appearance, disappearance, movable several variations of target, and take above-mentioned analysis as basic event processing mechanism.
1) between described frame, correlation analysis judges that target enters or the method that helps digestion is specially: definition PreList is the list structure of having stored all vehicle locations of present frame previous frame, P1~Pm is its element, CurList has stored the vehicle location of present frame, and element is C1~Cn.In calculating PreList, the rectangle coincidence factor of target Cj in target P i and CurList, sets certain threshold value, in the time that coincidence factor is greater than this threshold value, thinks that Pi and Cj belong to same movable vehicle target.Represent the relationship by objective (RBO) of two interframe with a matrix, the target intersection that is considered to belong to same vehicle is designated as 1, otherwise is designated as 0, can clearly be seen that like this relation of target between consecutive frame.First mate respectively PreList by each target in CurList, find the target that can match.If there is the target that cannot mate PreList, illustrate that this is a target not occurring before.Next remove respectively to mate CurList by each target in PreList again.If there is the target that cannot mate any CurList element, illustrate that this target disappears at present frame.
2) described static, the dbjective state of advancing determination methods is specially: the present invention's joining day factor in relation judgement between frame, judge temporary transient static phenomenon that vehicle target deceleration or short stay cause or more permanent static, and stop.Image is processed frame by frame, so replace timing operation with statistics frame number here.In the time that the position of same target between consecutive frame coincidence factor is very large, represent that its speed is obviously slowing down, at this moment can start this object count.If enough large (as being greater than threshold value Th1) of position coincidence factor in subsequent frame, counting adds one, otherwise subtracts for one (count value is not less than zero).If the stop of long period, coincidence factor will keep high value always, and the duration that exceedes Th1 is T2; And if target is just slowed down or brief stay, coincidence factor is only greater than Th1 in the time T 1 of a section very short.If the continuous a very long time T2 of target is still in same position, count value can increase gradually, once exceed a certain threshold value (as Th2), can judge that target is static; If target is temporary transient deceleration or the interior stop of short time T1 just,, after vehicle starts to accelerate, count value can start to successively decrease, and the current possibility remaining static is decay thereupon also.Final count value exceedes after threshold value Th2, and state transition occurs, and this vehicle is judged as static.In like manner, originally static vehicle is in the time preparing to start, and speed increases progressively starting, and count value can start to successively decrease subsequently, is then less than threshold value Th2 and enters travel condition, and it is zero that final timer is replied.A upper limit Max of count value definition who is necessary for target, otherwise vehicle remains static, the value of hour counter will increase always.Pass through static for a long time, vehicle start time state variation cannot be detected in time.
3) described event processing mechanism is specially: the list CarList of definition store car target, for preserve positional information and the count value of vehicle simultaneously, dynamically maintains the up-to-date information of vehicle simultaneously.By the object listing of front and back two frames, i.e. PreList and CurList, after mating, infers corresponding state variation, then upgrades the positional information sum counter in CarList.Front and back two interframe are contrast each other mutually, the position coincidence factors before and after calculating respectively.The target that loses coupling is have target to occur or disappear.The target that coincidence factor is on the low side thinks that its possibility in static is very little, and their counter successively decreases; The target that coincidence factor is very high thinks that very likely, in static, its counter increases progressively.Judge count value, check whether to have and stop or the generation of startup event.After judging object event and having recorded status information, then send corresponding information to system interface, and upgrade interface display, inform vehicle and parking space state that user is current.
The beneficial effect of technical scheme provided by the invention is:
The invention provides a kind of based under the environment of parking lot, adopt vehicle tracking and the detection method of intelligent video monitoring means, by the target vehicle detection in parking lot, and exterior contour is definite, final by analyzing the association between image in video, judge the object state of vehicle, enter, stop, or occupy-place is abnormal etc., complete the intelligent monitoring task for parking lot environment substantially, the drawback while avoiding pure manual monitoring.
Accompanying drawing explanation
A kind of vehicle tracking based on parking lot circumstance video monitoring of Fig. 1 and the schematic flow diagram of detection method.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
The situations such as the carelessness while facing many control points for manual monitoring, the present invention has designed a kind of algorithm of the intellectual analysis parking lot vehicle-state based on parking lot video monitoring, referring to Fig. 1, described below:
The vehicle detection of intelligent video monitoring and a track algorithm under the environment of parking lot, comprising: the detection of vehicle in video, and the tracking in vehicle operating path, the acquisition of vehicle-state.
With reference to Fig. 1, under the environment of a kind of parking lot, vehicle detection and the track algorithm of intelligent video monitoring comprise the following steps:
101: by video, extract reliably can real-time update background, and detect vehicle target based on improving background subtraction separating method.
102: background subtraction point-score is obtained to target vehicle and carry out morphology denoising.
103: draw the vehicle target profile obtaining by improvement background subtraction separating method so that tracking target.
104: by analyzing the relevance between video each two field picture, behavior the statistics that registration analysis obtains vehicle feeds back to monitoring management personnel.
In sum, the embodiment of the present invention provides vehicle detection and the track algorithm of intelligent video monitoring under the environment of a kind of parking lot, by detecting the vehicle target in the environment of parking lot, obtain target by outline, final by the frame association analysis in certain hour, judge the state of vehicle, and status information is issued and is used for pointing out monitor staff, thereby avoid manual monitoring in the time of many control points, cannot monitor preferably the drawback of whole monitoring objectives, completed intelligent supervision and replaced manual monitoring.
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, the invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
The foregoing is only preferred embodiment of the present invention, in order to limit the present invention, within the spirit and principles in the present invention not all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (3)
1. vehicle tracking and the detection method based on parking lot circumstance video monitoring, it comprises: comprise the vehicle checking method of improvement background subtraction separating method and the structure update strategy of background that the threshold value based on RGB color space is divided, and acquisition detects the morphology noise reduction process after target, extraction based on motion feature and matching process are determined the region of target travel, the behavioural analysis of vehicle, the processing of the judgement of vehicle-state and vehicle behavior event.
2. a kind of vehicle tracking and detection method based on parking lot circumstance video monitoring according to claim 1, is characterized in that, described method comprises: the vehicle checking method of the improvement background subtraction separating method that the threshold value based on RGB color space is divided;
The vehicle checking method of the improvement background subtraction separating method that the described threshold value based on RGB color space is divided comprises: the update strategy of initial background structure and background, to obtain the background information dynamically updating, think that the background work of wiping out provides reliable background; Threshold value division methods based on RGB color space replaces the gray level image after transforming to carry out difference operation, to overcome the problem of interference of gray scale similarity; Based on corrosion and the basic denoising of expanding and the combination denoising based on ' open and close ', more perfectly detect target to obtain.
3. a kind of vehicle tracking and detection method based on parking lot circumstance video monitoring according to claim 1, is characterized in that, tracking and the behavioural analysis of described method vehicle comprise:;
Tracking and the behavioural analysis of described vehicle comprise: use target external outline line, then draw out the vehicle target tracking of the boundary rectangle that can surround profile according to this group outline line; The Main Basis of analyzing vehicle target state variation is that the change in location rule of target in whole active procedure is by target location incidence matrix between definition frame, and cover correlation analysis and determine the method for dbjective state by position, analyze appearance, disappearance, movable several variations of target, and take above-mentioned analysis as basic event processing mechanism.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210403965.6A CN103778785A (en) | 2012-10-23 | 2012-10-23 | Vehicle tracking and detecting method based on parking lot environment video monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210403965.6A CN103778785A (en) | 2012-10-23 | 2012-10-23 | Vehicle tracking and detecting method based on parking lot environment video monitoring |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103778785A true CN103778785A (en) | 2014-05-07 |
Family
ID=50570969
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210403965.6A Pending CN103778785A (en) | 2012-10-23 | 2012-10-23 | Vehicle tracking and detecting method based on parking lot environment video monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103778785A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335986A (en) * | 2015-09-10 | 2016-02-17 | 西安电子科技大学 | Characteristic matching and MeanShift algorithm-based target tracking method |
CN105427420A (en) * | 2015-11-16 | 2016-03-23 | 深圳市捷顺科技实业股份有限公司 | Method and system for detecting vehicle exit and entrance states |
CN107066929A (en) * | 2017-01-06 | 2017-08-18 | 重庆大学 | The manifold freeway tunnel Parking hierarchical identification method of one kind fusion |
CN107402389A (en) * | 2016-05-18 | 2017-11-28 | 电装波动株式会社 | Arithmetic processing apparatus, arithmetic processing method and the medium for being stored with computer program |
CN109948436A (en) * | 2019-02-01 | 2019-06-28 | 深兰科技(上海)有限公司 | The method and device of vehicle on a kind of monitoring road |
CN110009929A (en) * | 2019-03-15 | 2019-07-12 | 北京筑梦园科技有限公司 | A kind of Vehicle berth management method, equipment and system |
CN110021172A (en) * | 2019-05-06 | 2019-07-16 | 北京英泰智科技股份有限公司 | A kind of vehicle total factor method for collecting characteristics and system |
CN111340840A (en) * | 2020-02-28 | 2020-06-26 | 浙江大华技术股份有限公司 | Method, equipment and device for determining relative movement speed of target object |
CN113591666A (en) * | 2021-07-26 | 2021-11-02 | 深圳创联时代电子商务有限公司 | Control method and device applied to mobile phone, computer readable medium and mobile phone |
WO2022134120A1 (en) * | 2020-12-26 | 2022-06-30 | 西安科锐盛创新科技有限公司 | Target motion prediction-based parking lot management and control method, apparatus, and electronic device |
CN116469059A (en) * | 2023-06-20 | 2023-07-21 | 松立控股集团股份有限公司 | Parking lot entrance and exit vehicle backlog detection method based on DETR |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101261681A (en) * | 2008-03-31 | 2008-09-10 | 北京中星微电子有限公司 | Road image extraction method and device in intelligent video monitoring |
CN101266689A (en) * | 2008-04-23 | 2008-09-17 | 北京中星微电子有限公司 | A mobile target detection method and device |
CN101290682A (en) * | 2008-06-25 | 2008-10-22 | 北京中星微电子有限公司 | Movement target checking method and apparatus |
CN101635835A (en) * | 2008-07-25 | 2010-01-27 | 深圳市信义科技有限公司 | Intelligent video monitoring method and system thereof |
CN101916448A (en) * | 2010-08-09 | 2010-12-15 | 云南清眸科技有限公司 | Moving object detecting method based on Bayesian frame and LBP (Local Binary Pattern) |
CN102034240A (en) * | 2010-12-23 | 2011-04-27 | 北京邮电大学 | Method for detecting and tracking static foreground |
US20110280442A1 (en) * | 2010-05-13 | 2011-11-17 | Hon Hai Precision Industry Co., Ltd. | Object monitoring system and method |
US20120020519A1 (en) * | 2010-07-21 | 2012-01-26 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and storage medium |
-
2012
- 2012-10-23 CN CN201210403965.6A patent/CN103778785A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101261681A (en) * | 2008-03-31 | 2008-09-10 | 北京中星微电子有限公司 | Road image extraction method and device in intelligent video monitoring |
CN101266689A (en) * | 2008-04-23 | 2008-09-17 | 北京中星微电子有限公司 | A mobile target detection method and device |
CN101290682A (en) * | 2008-06-25 | 2008-10-22 | 北京中星微电子有限公司 | Movement target checking method and apparatus |
CN101635835A (en) * | 2008-07-25 | 2010-01-27 | 深圳市信义科技有限公司 | Intelligent video monitoring method and system thereof |
US20110280442A1 (en) * | 2010-05-13 | 2011-11-17 | Hon Hai Precision Industry Co., Ltd. | Object monitoring system and method |
US20120020519A1 (en) * | 2010-07-21 | 2012-01-26 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and storage medium |
CN101916448A (en) * | 2010-08-09 | 2010-12-15 | 云南清眸科技有限公司 | Moving object detecting method based on Bayesian frame and LBP (Local Binary Pattern) |
CN102034240A (en) * | 2010-12-23 | 2011-04-27 | 北京邮电大学 | Method for detecting and tracking static foreground |
Non-Patent Citations (1)
Title |
---|
韩延玲: "智能交通***中视频车辆检测与定位技术研究", 《中国优秀硕士学位论文全文数据库(电子期刊)》, no. 11, 15 November 2011 (2011-11-15), pages 138 - 673 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335986A (en) * | 2015-09-10 | 2016-02-17 | 西安电子科技大学 | Characteristic matching and MeanShift algorithm-based target tracking method |
CN105335986B (en) * | 2015-09-10 | 2018-11-30 | 西安电子科技大学 | Method for tracking target based on characteristic matching and MeanShift algorithm |
CN105427420A (en) * | 2015-11-16 | 2016-03-23 | 深圳市捷顺科技实业股份有限公司 | Method and system for detecting vehicle exit and entrance states |
CN107402389A (en) * | 2016-05-18 | 2017-11-28 | 电装波动株式会社 | Arithmetic processing apparatus, arithmetic processing method and the medium for being stored with computer program |
CN107066929A (en) * | 2017-01-06 | 2017-08-18 | 重庆大学 | The manifold freeway tunnel Parking hierarchical identification method of one kind fusion |
CN109948436B (en) * | 2019-02-01 | 2020-12-08 | 深兰科技(上海)有限公司 | Method and device for monitoring vehicles on road |
CN109948436A (en) * | 2019-02-01 | 2019-06-28 | 深兰科技(上海)有限公司 | The method and device of vehicle on a kind of monitoring road |
CN110009929A (en) * | 2019-03-15 | 2019-07-12 | 北京筑梦园科技有限公司 | A kind of Vehicle berth management method, equipment and system |
CN110021172A (en) * | 2019-05-06 | 2019-07-16 | 北京英泰智科技股份有限公司 | A kind of vehicle total factor method for collecting characteristics and system |
CN111340840A (en) * | 2020-02-28 | 2020-06-26 | 浙江大华技术股份有限公司 | Method, equipment and device for determining relative movement speed of target object |
WO2022134120A1 (en) * | 2020-12-26 | 2022-06-30 | 西安科锐盛创新科技有限公司 | Target motion prediction-based parking lot management and control method, apparatus, and electronic device |
CN113591666A (en) * | 2021-07-26 | 2021-11-02 | 深圳创联时代电子商务有限公司 | Control method and device applied to mobile phone, computer readable medium and mobile phone |
CN116469059A (en) * | 2023-06-20 | 2023-07-21 | 松立控股集团股份有限公司 | Parking lot entrance and exit vehicle backlog detection method based on DETR |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103778785A (en) | Vehicle tracking and detecting method based on parking lot environment video monitoring | |
CN100593335C (en) | Motion detection method and device | |
CN102665071B (en) | Intelligent processing and search method for social security video monitoring images | |
CN103714325B (en) | Left object and lost object real-time detection method based on embedded system | |
CN100531374C (en) | Chroma deviation and brightness deviation combined video moving object detection method | |
CN103942850B (en) | Based on medical personnel's monitoring method on duty of video analysis and RFID technique | |
CN102833464B (en) | Method for structurally reconstructing background for intelligent video monitoring | |
CN101739827B (en) | Vehicle detecting and tracking method and device | |
CN102663362B (en) | Moving target detection method based on gray features | |
CN101621615A (en) | Self-adaptive background modeling and moving target detecting method | |
CN101303727A (en) | Intelligent management method based on video human number Stat. and system thereof | |
CN101188743A (en) | An intelligent digital system based on video and its processing method | |
CN103123726B (en) | A kind of target tracking algorism analyzed based on motor behavior | |
CN103729858A (en) | Method for detecting article left over in video monitoring system | |
CN101441712A (en) | Flame video recognition method and fire hazard monitoring method and system | |
CN109087363B (en) | HSV color space-based sewage discharge detection method | |
CN104063885A (en) | Improved movement target detecting and tracking method | |
CN107067595B (en) | State identification method and device of indicator light and electronic equipment | |
CN102568003A (en) | Multi-camera target tracking method based on video structural description | |
CN110415268A (en) | A kind of moving region foreground image algorithm combined based on background differential technique and frame difference method | |
CN107909599A (en) | A kind of object detecting and tracking system | |
CN101483763A (en) | Digital video processing method oriented to social security monitoring and apparatus thereof | |
CN102496281A (en) | Vehicle red-light violation detection method based on combination of tracking and virtual loop | |
CN102892007A (en) | Method and system for facilitating color balance synchronization between a plurality of video cameras as well as method and system for obtaining object tracking between two or more video cameras | |
CN103679690A (en) | Object detection method based on segmentation background learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140507 |