CN101303727B - Intelligent management method based on video human number Stat. and system thereof - Google Patents
Intelligent management method based on video human number Stat. and system thereof Download PDFInfo
- Publication number
- CN101303727B CN101303727B CN2008101163123A CN200810116312A CN101303727B CN 101303727 B CN101303727 B CN 101303727B CN 2008101163123 A CN2008101163123 A CN 2008101163123A CN 200810116312 A CN200810116312 A CN 200810116312A CN 101303727 B CN101303727 B CN 101303727B
- Authority
- CN
- China
- Prior art keywords
- people
- video
- area
- mrow
- module
- 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.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000010276 construction Methods 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 241000238631 Hexapoda Species 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 210000000746 body region Anatomy 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of video image processing and mode identifying. The invention discloses an intelligent management method based on video people number statistics, which includes the following steps: S1: capturing a video flow image as an input image; S2: carrying out the treatment of people number statistics on the input image to obtain the people flow distribution data in the unit time of each area; S3: a control center carries out adjusting and control on the working personnel according to the people flow distribution data obtained in step S2. A corresponding system includes a video collection module and a people number detecting statistics module; wherein, the people number detecting statistics module include a background construction module, a motion detecting module, an area analyzing module and a data statistics module. The method can be used for reasonably arranging the working number of the personnel of different posts according to the people flow statistic in a scene in a unit time, can better and more reasonably save the manpower cost and effectively improve the management level of public areas.
Description
Technical Field
The invention relates to the technical field of video image processing and mode recognition, in particular to an intelligent management method and system based on video people counting.
Background
With the increasing level of information management, statistics of passenger flow volume data such as real-time passenger flow volume estimation, passenger flow distribution analysis, congestion degree estimation and the like for places with huge passenger flow volumes such as supermarkets, shopping malls, stations, banks and the like becomes an effective way for providing first-hand background data for public area management. To solve this problem, the need of highly efficient management is far from being satisfied by relying solely on monitoring equipment and artificial judgment processing, and effective video image processing and data statistical methods and techniques become the key to improve the management level of public areas.
In the aspect of carrying out target statistics by means of dynamic video data, the invention patent with application number 03109626.3 and name of 'automatic counting system for tiny insects' discloses an automatic counting system for tiny insects, which belongs to the field of automatic measurement and counting, wherein the automatic counting system is operated according to the following steps of 1. image acquisition, namely, acquiring images of insects by using a digital camera or a combination device of a CCD camera and an image acquisition card and sending the images into the input end of a computer; 2. processing the image data by using a computer program to convert the color image into a gray image; 3. carrying out threshold segmentation on the gray level image to obtain a binary image; 4. carrying out connected region marking on the binary image; 5. carrying out target body identification and non-target body filtering; 6. counting the number of insects contained in the communicated area; 7. and displaying the counting result to the user.
However, the above invention only realizes the automatic counting of a specific target in a specific background environment and a specific area, and the counting technology for the specific target cannot meet the statistical requirements of the public area for the varying pedestrian volume under various different background environments.
Disclosure of Invention
The present invention has been made to solve the above problems.
The invention aims to provide an intelligent management method and system based on video people counting.
The intelligent management method based on the video people counting comprises the following steps:
firstly, a video stream image of a monitored area is obtained as an input image.
Then, carrying out motion detection on the input image, and analyzing and estimating the number of people in each motion area according to the motion detection result so as to obtain people stream distribution data of each area in unit time; the region analysis method adopts an overlapping degree calculation method and a similarity calculation method. And the similarity calculation method is that the similarity coefficient of the color features
And when the detected motion area is larger than the second threshold value, the two detected motion areas are determined as the same target. Wherein the second threshold is greater than 0 and less than 1. And the color feature similarity coefficient satisfies
Wherein,
the color probability distribution of any two motion areas is respectively, and the color probability distribution satisfies,
wherein,
i is 1, …, n is the image point set of the human target ellipse area, mu0Is the center of the human target ellipse, sigma0Is a parameter matrix, function, of the major and minor axes of an ellipse
R2→ 1, a, m is a pixelU is the discretization level of the color component, C is the normalization constant, δ is the kronecker delta function, N (·) is the gaussian kernel function, and m is the gray scale.
And finally, the control center regulates and controls the staff according to the people flow distribution data obtained in the step S2.
The intelligent management system based on the video people counting comprises a video acquisition module, a people number detection and counting module and a control center.
The video acquisition module is used for acquiring video stream images of a monitoring area and taking the video stream images as input images.
The people number detection and statistics module is used for carrying out motion detection on the input image, and analyzing and estimating the number of people in each motion area according to the motion detection result so as to obtain people stream distribution data of each area in unit time. Wherein the area analysis adopts an overlap meterA calculation and similarity calculation method; and the similarity calculation method is that the similarity coefficient of the color features
And when the detected motion area is larger than the second threshold value, the two detected motion areas are determined as the same target. Wherein the second threshold is greater than 0 and less than 1. And the color feature similarity coefficient satisfiesWherein,
the color probability distribution of any two motion areas is respectively, and the color probability distribution satisfies,
wherein,
i is 1, …, n is human target ellipsoidSet of field points, μ0Is the center of the human target ellipse, sigma0Is a parameter matrix, function, of the major and minor axes of an ellipse
R2→ 1, a, m is a pixelU is the discretization level of the color component, C is the normalization constant, δ is the kronecker delta function, N (·) is the gaussian kernel function, and m is the gray scale.
And the control center regulates and controls the staff according to the people flow distribution data.
The intelligent management method and the system based on the video people number statistics can be applied to real-time estimation of the number of customers, analysis of passenger flow distribution, estimation of crowding degree and the like in various occasions such as supermarkets, shopping malls, stations, banks and the like, and the important application of the intelligent video monitoring can greatly improve the management level of public areas.
Drawings
FIG. 1 shows a block diagram of the system of the present invention;
fig. 2 is a block diagram of the people detection statistic module according to the present invention.
Detailed Description
The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Aiming at a common video monitoring scene, the invention obtains the motion areas in the video stream by a motion detection method, preliminarily estimates the number of human bodies in each motion area and segments the multi-person area on the basis of area analysis, then tracks all the motion areas in the field by adopting a target tracking method, accurately counts the number of people in the image, reasonably arranges the number of the staff on duty at different posts according to the people stream statistic value in the scene in unit time period, better reasonably saves the labor cost and reduces the queuing waiting time of customers.
FIG. 1 is a system block diagram of the present invention. As shown in the figure, the system mainly comprises a video acquisition module, a people number detection and statistics module and a control center. In addition, the system also comprises staff calling equipment, a cash desk, a warehouse, promotion and the like.
The main function of the video acquisition module is to shoot a monitored scene and acquire video stream images, and the function of the module can be realized by shooting and capturing the video stream images through a special monitoring camera or a traditional camera.
The people number detection module has the main function of detecting the number of people in an input image in a unit time period, can adopt various existing motion detection technologies, such as a background difference method, an inter-frame difference method, a mixed Gaussian background difference and the like, statistically outputs the number of people in the input image through a series of data processing according to an input video stream, and obtains people flow distribution data of each region in the unit time.
Video stream images acquired by a network camera or a video camera are respectively used as input images, people number detection and statistics modules are used for obtaining people stream distribution of each section of the supermarket in unit time, and a control center regulates and controls workers according to the distribution. For example, the control center sends information to a calling device carried by the staff, and arranges the information to a department with relatively intense staff, such as a cash desk in a peak period, or arranges a warehouse to load goods on a shelf, so as to ensure sufficient goods to be sold on the shelf, or advertises the characteristics of the goods to customers, so as to promote sales of the goods.
Correspondingly, the intelligent management method based on the video people counting is realized by the following steps:
s1: acquiring a video stream image as an input image;
s2: carrying out people counting processing on the input image to obtain people flow distribution data of each region in unit time;
s3: and the control center regulates and controls the staff according to the people flow distribution data obtained in the step S2.
Fig. 2 is a block diagram of the people detection statistic module according to the present invention. As shown in FIG. 2, in the present invention, the people number detection and statistics module includes a background construction module, a motion detection module, an area analysis module and a data statistics module.
The background construction module is used for constructing a background model of an area to be monitored, and the simplest background model is a time average image, namely, an average image of the same scene in a period of time is used as the background model of the scene.
In a preferred embodiment of the invention, the background construction module is composed of a background modeling module and a background update module. The background modeling module is used for obtaining the gray value of each pixel point in the initial background image according to a plurality of frames collected from the image collecting equipment; the background updating module is used for judging whether the difference absolute value of the gray value of the pixel point with the same coordinate in the current frame and the previous frame is larger than a set threshold value, if so, B (x, y) is made to be alpha B1(x, y), if not, let B (x, y) be α B1(x, y) + (1-. alpha.) f (x, y). Wherein B (x, y) is the gray value of the pixel point with the coordinate (x, y) in the background image of the current frame; if the current frame is the 1 st frame after the frames collected by the image collecting device in the background modeling module, B1(x, y) is the gray value of the pixel point with the coordinate (x, y) in the initial background image, otherwise, is the gray value of the pixel point with the coordinate (x, y) in the background image of the previous 1 frame of the current frame; f (x, y) is the gray value of a pixel point with coordinates (x, y) in the current frame, alpha is a set parameter, and the value of alpha is more than or equal to 0 and less than or equal to 1.
In the motion detection module, for the current input image, firstly, the current input image is subtracted from the background image and the previous frame image respectively to obtain a difference image, and the two difference images are respectively subjected to binarization processing by using a thresholding method. Then, using mathematical morphology methods (such as expansion operation, erosion operation, on operation, off operation, etc.) to perform filtering processing on the two binary images, filling the holes in the foreground region, and simultaneously removing isolated regions and non-connected regions with small areas, and only keeping connected parts of the connected regions with the areas larger than a given threshold. And finally, performing logic and operation on the two filtered binary images, and performing mathematical morphology filtering processing on the operated images to obtain a final motion detection result. And after the motion detection result is obtained, updating the non-motion area according to the updating mode of the background difference method.
The main function of the region analysis module is to analyze whether each motion region is a single-person region or a multi-person region, and if so, to estimate the number of persons in the region and to divide the region into a plurality of single-person regions.
The invention realizes the estimation of the number of people by identifying the position of the top of the head of the people. Usually, the vertex of a person in a video image is generally visible, the position of the vertex of the person in a scene is determined by combining the geometric shape and the vertical projection of a motion area, and the number of people in the image is estimated so as to segment the crowd. First, the vertical projection of each binary region is calculated, and all local extreme points of the vertical projection are found. Then, all local extreme points are examined and if the projected value of an extreme point is greater than a given threshold, then it is considered a possible head vertex. And finally, merging all possible head vertexes, namely merging the possible head vertexes which are very close to each other in the horizontal direction into one head vertex to obtain a final head vertex.
After the estimation of the number of people in the area is realized, the multi-person area needs to be segmented. In a preferred embodiment of the invention, the multi-person region is segmented using an elliptical fit. The ratio of the width to the height of the human body is set as a fixed value l, the vertex of the head of the human body is used as an end point, a long axis is the same as the height of the human body, and an ellipse with the width-length ratio l surrounds the human body area to obtain a single-person area.
In the video monitoring process, a human body as a monitored target is generally in a motion state, so that the same target human body may be in different positions in different video image frames, especially in adjacent image frames, and thus the problem of target matching between two adjacent frames of the video image needs to be solved. The invention adopts a single-person region matching module to solve the problem of target matching between two adjacent frames. The method mainly adopts the methods of overlapping degree calculation and similarity calculation to realize the matching of the targets.
Overlap calculation
The invention judges whether two targets are matched or not by using the overlapping coefficient of the areas of the two targets of two adjacent frames, the motion speed of the human body is not too high in a general video monitoring system, and the overlapping degree of the same human body area in the two adjacent frames is high.
Let the rectangle occupied by any two regions be R1And R2Calculating R1And R2Overlap region R of1∩R2Then the overlap factor of the two regions is calculated according to the following formula:
where s (-) is an operator representing the calculated area. In actual calculation, a threshold Th1 greater than 0 and smaller than 1 can be set as required, and when r > Yh1, it can be considered that the two regions have the possibility of matching.
The mere dependence on area overlap for object correlation is often not accurate enough, so that with the help of more object features, in a preferred embodiment of the invention color feature similarity matching is chosen for further object correlation.
Similarity calculation
Set the image points of the human target elliptical region as1, …, n, centered at μ0Elliptic major and minor axis parameter matrix sigma0Wherein the long axis parameter h and the short axis parameter w define a functionR2→ 1.. m represents a pixel
The color value of (a). Then in the elliptical target area, the image point
Color probability distribution ofu-1, …, m. may be represented as:
where δ is a kronecker delta function, C is a normalization constant, and
n (-) is a gaussian kernel function and u is a color component discretization level.
Suppose that two target human body regions with the overlapping degree larger than the threshold are respectively Q1And Q2The color probability distribution of the two is respectively
And
their similarity can be measured by the bhattacharya coefficient, i.e.:
setting a threshold Th2 greater than 0 and less than 1, when ρ > Th2, two target regions are considered to be associated and the same target.
The data statistics module establishes a database of a person region database and is mainly responsible for recording the size, the position and the image characteristics of a scene in a unit time period and the number of people in the region for later application processing.
Because the entrance and exit of the supermarket have the characteristic of unidirectionality, in a specific embodiment of the invention, the region analysis module only carries out people counting on the whole image at the initial stage, the later counting is only carried out on the boundary region of the image, and the number of people in the whole scene is deduced according to the obtained number of people entering and exiting the scene by using methods with strong engineering such as Kalman filtering, template matching and the like.
Nall＝Nt-1+Nin-Nout
Wherein N isin，NoutRespectively the number of people entering and exiting the scene per unit time.
The intelligent management system based on the video people counting analyzes the video images in the monitoring scene based on the computer vision technology, counts and extracts the information of the people number in the scene, reasonably arranges the work distribution of workers, and has positive and effective effects on saving the labor cost, facilitating the customers, reducing the crowding of people, avoiding the unreasonable situations of long payment queuing time and the like.
Compared with the prior art, the invention has the following remarkable advantages:
1. the intelligent management system based on the video people counting has the advantages of high integration level, convenience in use and easiness in installation and maintenance.
2. The intelligent management system based on the video people counting, which is provided by the invention, embeds background updating, people detection and analysis at the front end, and only sends the people counting value to the control center, so that the intelligent management system has the advantages of small occupied bandwidth, small required storage space, good real-time performance, high system efficiency and stability.
3. The people counting and detecting module in the system has clear structure, clear division of work of each part, strong independence, simple and convenient calculation, high speed and easy hardware realization.
4. The control center module in the system is carefully considered, so that the labor cost is reasonably saved better, and the shopping by customers is facilitated.
5. In addition, the method for counting the number of people in a single frame is optimized by combining the target tracking method, so that the accuracy of the number counting is further improved.
Although the present invention has been described in connection with a specific embodiment, a person skilled in the art may make appropriate changes to some features of the present invention or apply the present invention to other fields to solve the above problems, and therefore all relevant extensions and applications made by the person skilled in the art on the basis of the present embodiment shall fall within the scope of the present application.
Claims (14)
1. An intelligent management method based on video people counting is characterized by comprising the following steps:
s1: acquiring a video stream image of a monitoring area as an input image;
s2: carrying out motion detection on the input image, and then analyzing and estimating the number of people in each motion area according to the motion detection result so as to obtain people stream distribution data of each area in unit time; wherein, the region analysis method adopts an overlapping degree calculation method and a similarity calculation method; and the similarity calculation method is as followsColor feature similarity coefficient
When the detected motion area is larger than the second threshold value, the two detected motion areas are determined as the same target; wherein the second threshold is greater than 0 and less than 1;
and the color feature similarity coefficient satisfies
Wherein,
the color probability distribution of any two motion areas is respectively, and the color probability distribution satisfies,
wherein,
i is 1, …, n is the image point set of the human target ellipse area, mu0Is the center of the human target ellipse, sigma0Is a parameter matrix, function, of the major and minor axes of an ellipse
R2→ 1, a, m is a pixel
U is the discretization grade of the color component, C is a normalization constant, delta is a kronecker delta function, N (-) is a Gaussian kernel function, and m is the gray scale;
s3: and the control center regulates and controls the staff according to the people flow distribution data obtained in the step S2.
2. The intelligent management method based on video people counting as claimed in claim 1, wherein in step S2,
firstly, a background model of a region to be monitored is constructed, and then the motion detection is carried out on the input image according to the obtained background model.
3. The intelligent management method based on video people counting as claimed in claim 2, characterized in that the background is updated regularly during the process of building the background model of the area to be monitored.
4. The intelligent management method based on video people counting as claimed in claim 1, wherein in the motion detection process, the final motion detection result is obtained by adopting the methods of differential image, binarization processing and filtering processing.
5. The intelligent management method based on the statistics of the number of people in the video according to claim 1, wherein in the process of analyzing each motion area, whether each motion area is a single-person area or a multi-person area is firstly analyzed, and then the number of people in the multi-person area is estimated and divided into a plurality of single-person areas.
6. The intelligent management method based on video people counting of claim 5, wherein when the multi-people region is divided, the multi-people region is divided by an ellipse fitting method.
7. The intelligent management method based on video people counting of claim 1, wherein the overlapping degree calculation method is that when the overlapping degree coefficient r is larger than a first threshold value, any two detected motion areas are determined to be matched, and the first threshold value is larger than 0 and smaller than 1;
the overlap factor r satisfies
Wherein R is1And R2Respectively rectangular areas, R, occupied by said two motion areas1∩R2Is R1And R2S (-) is the operator for calculating the area.
8. An intelligent management system based on video people counting is characterized by comprising a video acquisition module, a people number detection and counting module and a control center;
the video acquisition module is used for acquiring a video stream image of a monitoring area and taking the video stream image as an input image;
the people number detection and statistics module is used for carrying out motion detection on the input image, and analyzing and estimating the number of people in each motion area according to the motion detection result so as to obtain people stream distribution data of each area in unit time; wherein, the region analysis adopts an overlapping degree calculation method and a similarity calculation method; and the similarity calculation method is that the similarity coefficient of the color features
When the detected motion area is larger than the second threshold value, the two detected motion areas are determined as the same target; wherein the second threshold is greater than 0 and less than 1;
and the color feature similarity coefficient satisfiesWherein,
the color probability distribution of any two motion areas is respectively, and the color probability distribution satisfies,
wherein,i is 1, …, n is the image point set of the human target ellipse area, mu0In the ellipse of human body targetHeart, sigma0Is a parameter matrix, function, of the major and minor axes of an ellipse
R2→ 1, a, m is a pixelU is the discretization grade of the color component, C is a normalization constant, delta is a kronecker delta function, N (-) is a Gaussian kernel function, and m is the gray scale;
and the control center regulates and controls the staff according to the people flow distribution data.
9. The intelligent management system based on video people counting of claim 8, wherein the people detection statistics module comprises:
the background construction module is used for constructing a background model of the area to be monitored;
and the motion detection module is used for carrying out motion detection on the input image according to the background model.
10. The intelligent management system based on video people counting of claim 9, wherein the background construction module comprises a background modeling module for deriving a gray value of each pixel point in the initial background image from a plurality of frames collected from the video collection module, and a background update module for updating the background periodically.
11. The intelligent management system based on video people counting of claim 9, wherein the motion detection module obtains the final motion detection result by adopting a differential image, a binarization process and a filtering process.
12. The intelligent management system based on video people counting of claim 8, wherein the people detection statistics module analyzes whether each motion area is a single person area or a multi-person area, and estimates and segments the number of people in the multi-person area into a plurality of single person areas.
13. The intelligent video people counting-based management system according to claim 12, wherein the overlap calculation method is to determine that any two detected motion areas match when the overlap coefficient r is greater than a first threshold, and the first threshold is greater than 0 and less than 1;
the overlap factor r satisfiesWherein R is1And R2Respectively rectangular areas, R, occupied by said two motion areas1∩R2Is R1And R2S (-) is the operator for calculating the area.
14. The intelligent management system based on video people counting of claim 8, wherein the people detection and statistics module analyzes each motion region by counting the number of people in the whole image in an initial stage, and only performs statistics in a later stage on the boundary region of the image, and the people number in the whole scene is deduced according to the number of people getting in and out of the scene by means of Kalman filtering and a method with strong template matching engineering.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101163123A CN101303727B (en) | 2008-07-08 | 2008-07-08 | Intelligent management method based on video human number Stat. and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101163123A CN101303727B (en) | 2008-07-08 | 2008-07-08 | Intelligent management method based on video human number Stat. and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101303727A CN101303727A (en) | 2008-11-12 |
| CN101303727B true CN101303727B (en) | 2011-11-23 |
Family
ID=40113626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008101163123A Active CN101303727B (en) | 2008-07-08 | 2008-07-08 | Intelligent management method based on video human number Stat. and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101303727B (en) |
Families Citing this family (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420536B (en) * | 2008-11-28 | 2011-03-02 | 江苏科海智能系统有限公司 | Background image modeling method for video stream |
| CN101577812B (en) * | 2009-03-06 | 2014-07-30 | 北京中星微电子有限公司 | Method and system for post monitoring |
| CN102098491B (en) * | 2009-12-14 | 2014-05-21 | 北京中星微电子有限公司 | Monitoring method and device of chaotic scene |
| GB2476500B (en) | 2009-12-24 | 2012-06-20 | Infrared Integrated Syst Ltd | Activity mapping system |
| CN102063753A (en) * | 2011-01-18 | 2011-05-18 | 王芳 | Method for identification and statistic of visitors based on Internet of things |
| CN102496164B (en) * | 2011-11-14 | 2013-12-11 | 通号通信信息集团有限公司 | Event detection method and event detection system |
| CN102542289B (en) * | 2011-12-16 | 2014-06-04 | 重庆邮电大学 | Pedestrian volume statistical method based on plurality of Gaussian counting models |
| CN102609229B (en) * | 2012-02-16 | 2014-12-31 | 中国科学院声学研究所 | Graph parallel-updating method for embedded multi-window application |
| CN104376575B (en) * | 2013-08-15 | 2018-02-16 | 汉王科技股份有限公司 | A kind of pedestrian counting method and device based on multi-cam monitoring |
| CN104408746B (en) * | 2014-11-21 | 2017-07-14 | 安徽清新互联信息科技有限公司 | A kind of passenger flow statistical system based on depth information |
| CN104392522B (en) * | 2014-11-21 | 2016-08-24 | 安徽清新互联信息科技有限公司 | A kind of passenger flow statistical system based on pseudo-depth information |
| CN106295788B (en) | 2015-05-12 | 2019-01-08 | 杭州海康威视数字技术股份有限公司 | The statistical method and device of the volume of the flow of passengers |
| CN105466414B (en) * | 2015-11-17 | 2018-05-29 | 广东欧珀移动通信有限公司 | The recommendation method and server of a kind of navigation routine |
| CN105574499B (en) * | 2015-12-15 | 2019-08-20 | 东华大学 | A kind of number detection statistics method and system based on SOC |
| CN107025418A (en) * | 2016-01-29 | 2017-08-08 | 广州地铁集团有限公司 | Anti- detection method of stealing a ride, detecting system and its system based on image procossing |
| CN105489017B (en) * | 2016-02-04 | 2016-12-07 | 深圳亿维锐创科技股份有限公司 | Multifunctional traffic crossing electrical control cabinet |
| CN105722271B (en) * | 2016-02-04 | 2017-06-06 | 广东金南方新科技股份有限公司 | Intelligent automatic radiating electric control box |
| CN107180420A (en) * | 2016-03-09 | 2017-09-19 | 顺丰科技有限公司 | Article transmits householder method |
| CN107766784A (en) * | 2016-08-20 | 2018-03-06 | 宋坤骏 | A kind of novel video people counting algorithm |
| CN106304564A (en) * | 2016-09-28 | 2017-01-04 | 广东雅达电子股份有限公司 | A kind of wisdom Lighting Control Assembly based on image recognition and method |
| CN108537089B (en) * | 2017-03-01 | 2024-03-15 | 开利公司 | People flow estimation system and people flow estimation method |
| CN107481255B (en) * | 2017-08-08 | 2019-12-20 | 浙江大华技术股份有限公司 | Method and device for determining number of people |
| CN107292297A (en) * | 2017-08-09 | 2017-10-24 | 电子科技大学 | A kind of video car flow quantity measuring method tracked based on deep learning and Duplication |
| CN107368823A (en) * | 2017-08-23 | 2017-11-21 | 广州市九安光电技术股份有限公司 | A kind of stream of people's focus monitoring method and system based on panoramic picture |
| CN107680118B (en) * | 2017-08-29 | 2020-10-20 | 苏州佳世达光电有限公司 | Image identification tracking method |
| CN108345841B (en) * | 2018-01-23 | 2019-02-12 | 杭州视在科技有限公司 | A kind of intelligent filtering method of video image processing |
| CN108596938A (en) * | 2018-04-25 | 2018-09-28 | 杭州光珀智能科技有限公司 | A kind of passenger flow statistical method and device |
| CN110503284B (en) * | 2018-05-18 | 2022-08-05 | 杭州海康威视数字技术股份有限公司 | Statistical method and device based on queuing data |
| CN108921983B (en) * | 2018-05-22 | 2020-11-03 | 浙江大学山东工业技术研究院 | People flow statistical method for waiting room of complex equipment coal mine system |
| CN111290001A (en) | 2018-12-06 | 2020-06-16 | 杭州海康威视数字技术股份有限公司 | Target overall planning method, device and equipment based on GPS coordinates |
| CN109767454B (en) * | 2018-12-18 | 2022-05-10 | 西北工业大学 | Unmanned aerial vehicle aerial video moving target detection method based on time-space-frequency significance |
| CN109784462A (en) * | 2018-12-29 | 2019-05-21 | 浙江大华技术股份有限公司 | A kind of passenger number statistical system, method and storage medium |
| CN109840982B (en) * | 2019-01-02 | 2020-07-14 | 京东方科技集团股份有限公司 | Queuing recommendation method and device and computer readable storage medium |
| CN109920104B (en) * | 2019-01-18 | 2021-01-08 | 浙江万邦智能科技股份有限公司 | A access control system based on face identification for wisdom hospital |
| CN110545192B (en) * | 2019-01-25 | 2020-06-26 | 航天欧华信息技术有限公司 | Network cutting control device |
| CN111951169A (en) * | 2019-04-29 | 2020-11-17 | 泰州悦诚科技信息咨询中心 | Adaptive data correction method |
| CN112149457A (en) * | 2019-06-27 | 2020-12-29 | 西安光启未来技术研究院 | People flow statistical method, device, server and computer readable storage medium |
| CN110443153A (en) * | 2019-07-15 | 2019-11-12 | 清华大学 | Number calibration householder method and system towards monitor video in building |
| CN110488695B (en) * | 2019-08-09 | 2021-03-19 | 广州启盟信息科技有限公司 | Scheduling method and device based on people stream data |
| CN111680569B (en) * | 2020-05-13 | 2024-04-19 | 北京中广上洋科技股份有限公司 | Attendance rate detection method, device, equipment and storage medium based on image analysis |
| CN111881829A (en) * | 2020-07-28 | 2020-11-03 | 广州技诺智能设备有限公司 | Method and device for detecting personnel and calculating personnel number in public place and monitoring equipment |
| CN112203052A (en) * | 2020-09-30 | 2021-01-08 | 重庆天智慧启科技有限公司 | Security protection monitoring platform |
| CN113011280A (en) * | 2021-02-26 | 2021-06-22 | 清华大学 | Method and device for detecting person contact distance, computer equipment and storage medium |
| CN113516024A (en) * | 2021-04-26 | 2021-10-19 | 中国工商银行股份有限公司 | Multi-region people counting method and device |
| CN113592887B (en) * | 2021-06-25 | 2022-09-02 | 荣耀终端有限公司 | Video shooting method, electronic device and computer-readable storage medium |
| CN113762169A (en) * | 2021-09-09 | 2021-12-07 | 北京市商汤科技开发有限公司 | People flow statistical method and device, electronic equipment and storage medium |
| CN114004866B (en) * | 2022-01-04 | 2022-03-22 | 天津大学四川创新研究院 | Mosquito recognition system and method based on image similarity difference |
-
2008
- 2008-07-08 CN CN2008101163123A patent/CN101303727B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN101303727A (en) | 2008-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101303727B (en) | Intelligent management method based on video human number Stat. and system thereof | |
| CN102542289B (en) | Pedestrian volume statistical method based on plurality of Gaussian counting models | |
| CN106203513B (en) | A kind of statistical method based on pedestrian's head and shoulder multi-target detection and tracking | |
| CN102867177B (en) | A kind of demographic method based on gradation of image coupling | |
| CN103258232B (en) | A kind of public place crowd estimate's method based on dual camera | |
| WO2018119668A1 (en) | Method and system for recognizing head of pedestrian | |
| CN103310444B (en) | A kind of method of the monitoring people counting based on overhead camera head | |
| CN104933710A (en) | Intelligent analysis method of store people stream track on the basis of surveillance video | |
| CN104978567B (en) | Vehicle checking method based on scene classification | |
| CN103226860B (en) | Passage passenger traffic density estimation method | |
| CN102156880A (en) | Method for detecting abnormal crowd behavior based on improved social force model | |
| CN111353338B (en) | Energy efficiency improvement method based on business hall video monitoring | |
| CN106981150A (en) | A kind of supermarket's intelligent anti-theft system and method | |
| CN111681382A (en) | Method for detecting temporary fence crossing in construction site based on visual analysis | |
| Karpagavalli et al. | Estimating the density of the people and counting the number of people in a crowd environment for human safety | |
| CN103559481B (en) | People counting method under complex environment | |
| CN107483894A (en) | Judge to realize the high ferro station video monitoring system of passenger transportation management based on scene | |
| CN112257615B (en) | Customer number statistical method based on clustering | |
| Yen et al. | Abnormal event detection using HOSF | |
| CN106056078A (en) | Crowd density estimation method based on multi-feature regression ensemble learning | |
| Furuya et al. | Road intersection monitoring from video with large perspective deformation | |
| CN104123569B (en) | Video person number information statistics method based on supervised learning | |
| CN113920585A (en) | Behavior recognition method and device, equipment and storage medium | |
| CN113963373A (en) | Video image dynamic detection and tracking algorithm based system and method | |
| CN105989615A (en) | Pedestrian tracking method based on multi-feature fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20160516 Address after: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105 -478 Patentee after: GUANGDONG ZHONGXING ELECTRONICS CO., LTD. Address before: 100083 Haidian District, Xueyuan Road, No. 35, the world building, the second floor of the building on the ground floor, No. 16 Patentee before: Beijing Vimicro Corporation |