CN103020706A - Visitors flow rate statistic algorithm based on moving target detection and Haar characteristics - Google Patents
Visitors flow rate statistic algorithm based on moving target detection and Haar characteristics Download PDFInfo
- Publication number
- CN103020706A CN103020706A CN2011102824977A CN201110282497A CN103020706A CN 103020706 A CN103020706 A CN 103020706A CN 2011102824977 A CN2011102824977 A CN 2011102824977A CN 201110282497 A CN201110282497 A CN 201110282497A CN 103020706 A CN103020706 A CN 103020706A
- Authority
- CN
- China
- Prior art keywords
- people
- flow rate
- moving target
- target detection
- haar feature
- 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
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention provides a visitors flow rate statistic algorithm based on moving target detection and Haar characteristics and an application of the algorithm in intelligent security and protection. The method can effectively and correctly detect a moving target in an image and can recognize a head in the moving target so as to count, the counting of pedestrians in a region is obtained and intelligent video monitoring and intelligent judgment are achieved.
Description
Technical field
The invention belongs to computer vision field, the particularly traffic statistics algorithm of a kind of based on motion target detection and Haar feature, and the application of the method in intelligent security guard.
Technical background
Along with the development of society, demographics has more and more important meaning, and its range of application is also more and more extensive.For example, demographics under the special screne, demographics in the critical area, public transport is demographics etc. up and down.These regional numbers are taken precautions against public safety, and marketing decision and traffic disposition etc. has very important value.Traditional demographic method is artificial counting or artificial electronic equipment flip-flop number, and not only wasting manpower and material resources but also efficient are not high.Intelligent video monitoring system can be identified different moving object, and useful information can be provided in fast and the most best mode, so that its application aspect demographics becomes possibility.
Because common method still can not identify completely effectively to the pedestrian in video image and the low-resolution image, industry is demanded a kind of can the realization urgently and in the intelligent video monitoring pedestrian is identified, and the method for flow of the people being added up according to the zone.
Summary of the invention
The objective of the invention is for existing video monitoring system, existence can't be identified the pedestrian automatically, and the problem that is difficult to the critical areas such as gateway are carried out pedestrian's traffic statistics proposes the people flow rate statistical algorithm of a kind of based on motion target detection and Haar feature.
In order to realize goal of the invention, the technical scheme of employing is as follows:
The process flow diagram of algorithm as shown in Figure 1.
This flow process at first is moving target and the motion target area that extracts in the sequence of video images, then the motion target area that extracts is carried out the number of people and detects, and at last the number of people that detects is carried out the interior counting in zone.
This algorithm based on condition be that camera is in plumbness, extract motion target area after, utilize number of people detection algorithm that the target in the moving region is carried out the number of people and detect, and then by regional method of counting the number of people that detects is counted.Can be described below with this algorithm detailed process:
◆ image sequence is extracted moving target and moving region:
◆ the moving region and the target that extract are stored;
◆ utilize the Head recognition algorithm that the target in the moving region is carried out the number of people and detect;
◆ the number of people that detects is carried out regional counting algorithm it is counted;
This algorithm has effectively solved other algorithm in that seriously to block under the environment discrimination low, flase drop, the problem such as undetected can effectively be got rid of the flase drop problem that the number of people is similar to the number of people in detecting by moving target and extracted region, can be in different places, carry out people flow rate statistical under the varying environment.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, the below will do simple the introduction to the accompanying drawing of required use in embodiment or the description of the Prior Art, apparently, accompanying drawing in the following describes only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is architectural schematic of the present invention;
Fig. 2 is computing function synoptic diagram of the present invention.
Embodiment
As shown in Figure 2, be the computing function synoptic diagram of this algorithm.
Function of the present invention is based on up-to-date OpenCV storehouse.OpenCV is writing a Chinese character in simplified form of " Open Source Computer Vision Library ", is the Intel computer vision storehouse of increasing income.It is made of a series of C functions and a small amount of C++ class, is to realize that image is processed and a lot of general-purpose algorithms of computer vision aspect, can be used to common problem in the process computer vision field, wherein is mainly concerned with the content of the following aspects:
MotionDetect-moving object detection and extraction;
(2) UpdateMotionHistory-upgrades moving target
(3) Detect_And_Draw_Objects-Head recognition;
(4) StatisHumanNumber-demographics;
In the present invention, can be used to moving target is detected by function MotionDetect, extract motion target area;
Can use following manner to upgrade motion history image by function cvUpdateMotionHistory;
Function Detect_And_Draw_Objects is used for the moving region target is carried out Head recognition and detection, and the number of people that detects is deposited in an object chain;
Function CommonArea is used for judging whether two targets are same target, when the ratio of the coincidence area of two targets and area own reaches certain threshold value, just judges that both are same target;
Function IsPointOnLine is used for judging the relation of number of people target's center's point and definition wires, function return value is for just when number of people central point is positioned at the definition wires left side, function return value is for negative when number of people central point is positioned at definition wires the right, when number of people central point was positioned on the definition wires, function return value was zero;
Function StatisHumanNumber is used for the number of people to detecting, thereby judges whether they stride across our defined zone and count.
Claims (4)
1. the people flow rate statistical algorithm of a based on motion target detection and Haar feature, thus it is characterized in that utilizing simultaneously Detection for Moving Target the moving object in the video image is identified and to be utilized the Haar feature to realize the number of people in the moving target identified and realize the feature of flow of the people is added up.
2. the people flow rate statistical algorithm of a based on motion target detection and Haar feature is characterized in that proposing a kind of new image pre-service solution for stream of people's statistics.
3. the people flow rate statistical algorithm of a based on motion target detection and Haar feature is characterized in that utilizing and improves the Haar feature and realize the number of people in the moving target in the high-resolution data source is advanced to extract.
4. the people flow rate statistical algorithm of a based on motion target detection and Haar feature according to claim 2 with claim 3, is characterized in that, utilizes the method that detects the path that the flow of the people in inconsiderate path in the scene is added up.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011102824977A CN103020706A (en) | 2011-09-20 | 2011-09-20 | Visitors flow rate statistic algorithm based on moving target detection and Haar characteristics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011102824977A CN103020706A (en) | 2011-09-20 | 2011-09-20 | Visitors flow rate statistic algorithm based on moving target detection and Haar characteristics |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103020706A true CN103020706A (en) | 2013-04-03 |
Family
ID=47969292
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011102824977A Pending CN103020706A (en) | 2011-09-20 | 2011-09-20 | Visitors flow rate statistic algorithm based on moving target detection and Haar characteristics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103020706A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104008396A (en) * | 2014-05-22 | 2014-08-27 | 南京邮电大学 | In and out people flow statistical method based on people head color and shape features |
CN109117741A (en) * | 2018-07-20 | 2019-01-01 | 苏州中德宏泰电子科技股份有限公司 | Offline object identifying method and device to be detected |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080130952A1 (en) * | 2002-10-17 | 2008-06-05 | Siemens Corporate Research, Inc. | method for scene modeling and change detection |
CN102147869A (en) * | 2011-03-31 | 2011-08-10 | 上海交通大学 | Pedestrian detection method based on foreground analysis and pattern recognition |
-
2011
- 2011-09-20 CN CN2011102824977A patent/CN103020706A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080130952A1 (en) * | 2002-10-17 | 2008-06-05 | Siemens Corporate Research, Inc. | method for scene modeling and change detection |
CN102147869A (en) * | 2011-03-31 | 2011-08-10 | 上海交通大学 | Pedestrian detection method based on foreground analysis and pattern recognition |
Non-Patent Citations (3)
Title |
---|
徐麒等: "基于视频图像的人脸检测与统计", 《计算机与现代化》 * |
顾德军: "基于视频图像处理的人数自动统计技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
顾德军等: "一种基于人头特征的人数统计方法研究", 《机械制造与自动化》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104008396A (en) * | 2014-05-22 | 2014-08-27 | 南京邮电大学 | In and out people flow statistical method based on people head color and shape features |
CN109117741A (en) * | 2018-07-20 | 2019-01-01 | 苏州中德宏泰电子科技股份有限公司 | Offline object identifying method and device to be detected |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9460361B2 (en) | Foreground analysis based on tracking information | |
CN103246896B (en) | A kind of real-time detection and tracking method of robustness vehicle | |
US10445567B2 (en) | Pedestrian head identification method and system | |
CN108052859B (en) | Abnormal behavior detection method, system and device based on clustering optical flow characteristics | |
Huang et al. | An intelligent strategy for checking the annual inspection status of motorcycles based on license plate recognition | |
CN103116987B (en) | Traffic flow statistic and violation detection method based on surveillance video processing | |
CN102231236B (en) | Method and device for counting vehicles | |
CN106446926A (en) | Transformer station worker helmet wear detection method based on video analysis | |
Zhang et al. | Application of deep learning and unmanned aerial vehicle technology in traffic flow monitoring | |
Li et al. | Abandoned objects detection using double illumination invariant foreground masks | |
CN102867177B (en) | A kind of demographic method based on gradation of image coupling | |
Antić et al. | K-means based segmentation for real-time zenithal people counting | |
CN103971380A (en) | Pedestrian trailing detection method based on RGB-D | |
CN104200466A (en) | Early warning method and camera | |
CN102902957A (en) | Video-stream-based automatic license plate recognition method | |
CN103020577B (en) | Moving target identification method based on hog characteristic and system | |
CN104573811A (en) | Pedestrian flow counting method based on infrared image and color image fusion | |
CN116153086B (en) | Multi-path traffic accident and congestion detection method and system based on deep learning | |
CN111062319B (en) | Driver call detection method based on active infrared image | |
CN106250846A (en) | A kind of public security image method for detecting based on video monitoring | |
CN104239908A (en) | Intelligent ridership automatic statistical method based on self-adaptive threshold value | |
CN116311166A (en) | Traffic obstacle recognition method and device and electronic equipment | |
Chen et al. | A computer vision algorithm for locating and recognizing traffic signal control light status and countdown time | |
CN113901946A (en) | Abnormal behavior detection method and device, electronic equipment and storage medium | |
CN103020706A (en) | Visitors flow rate statistic algorithm based on moving target detection and Haar characteristics |
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: 20130403 |