CN106650695A - Video analysis technology-based people flow tracking statistics system - Google Patents
Video analysis technology-based people flow tracking statistics system Download PDFInfo
- Publication number
- CN106650695A CN106650695A CN201611256466.3A CN201611256466A CN106650695A CN 106650695 A CN106650695 A CN 106650695A CN 201611256466 A CN201611256466 A CN 201611256466A CN 106650695 A CN106650695 A CN 106650695A
- Authority
- CN
- China
- Prior art keywords
- module
- people
- human body
- human
- track
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a video analysis technology-based people flow tracking statistics system. The system comprises a camera, a storage module, a comparison module, a locating module, a track forming module, a direction module, a counting module, a calculation module, a pre-built human body identification model and a preset motion track, wherein the comparison module compares image information obtained by the camera with a stored human body identification model; if the comparison succeeds, first-step locating is performed; the track forming module tracks the identified human body image information based on the first-step locating to form a human body moving track in a three-dimensional space; the direction module compares the human body moving track with the preset motion track in the storage module to determine a direction of the human body moving track; and the counting module performs statistics on people flow according to the direction of the human body moving track. According to the system, the coming and going of people can be accurately identified and the direction can be accurately determined, so that the false alarm rate is relatively low.
Description
Technical field
The present invention relates to Video Analysis Technology field, and in particular to a kind of tracking based on Video Analysis Technology counts the stream of people
The system of amount.
Background technology
With the development of Video Supervision Technique, video monitoring system is all provided with the gateway of many public places, with
Just administrative staff are monitored and count flow of the people to these public place gateways.Field is consumed in supermarket, shop, market etc.
Institute, flow of the people has important meaning to manager.
Traditional people flow rate statistical is that, using two kinds of infrared counting device and mechanical counter, infrared counting device utilizes infrared sense
Answer device sensing to carry out counting statistics through personnel, but when more by personnel, some personnel because blocking, it is difficult to red
Outer inductor is sensed, and infrared counting device INTELLIGENT IDENTIFICATION someone passes in and out, it is impossible to determine direction, easily wrong report, precision compared with
It is low.Mechanical counter needs sense pedal embedded in passway, and touching counter by pedal carries out personnel counting,
This mode counts inaccurate when flow of the people is larger, and the number that simply rough statistics is passed through, and cannot be true
The fixed personnel for passing through enter or go out.
In order to solve the above problems, use based on the people flow rate statistical method of video analysis, at present, based on video analysis
Flow statistical method mainly have three classes：
One is the method for distinguished point based tracking, first tracks some motion characteristics points, and then the track of characteristic point is entered
Row cluster analysis, so as to obtain flow of the people information, characteristic point is difficult to stably track in itself, and technology acuracy is poor.
Two is, based on the tracking of human body segmentation, moving target block to be extracted first, and then moving target block is carried out
Segmentation obtains single human body target, finally tracks each human body target and realizes people flow rate statistical.If blocking shape when human body is in
During state, the accuracy of human body segmentation is difficult to be guaranteed, and affects statistical accuracy.
Three is the method based on the number of people or head and shoulder detect and track, and the method detects in video the number of people or head and shoulder,
People flow rate statistical is carried out by the tracking to the number of people or head and shoulder.The method can only detect same class target, it is impossible to while detection
Inhomogeneity target.
The content of the invention
It is an object of the invention to overcome the problem above that prior art is present, there is provided a kind of based on video analysis pattern
The system of tracking statistics flow of the people, the system of the present invention is not only able to accurately recognize someone's turnover, but also the side of can determine
To rate of false alarm is relatively low.
To realize above-mentioned technical purpose, above-mentioned technique effect is reached, the present invention is achieved through the following technical solutions：
A kind of system of the tracking statistics flow of the people based on Video Analysis Technology, it includes：
Camera, the camera obtains image information；
Memory module, the human bioequivalence model that the memory module storage pre-builds, the memory module also stores pre-
The movement locus of first self-defined setting；
Contrast module, the image information that the contrast module obtains the camera and storage in the memory module
Human bioequivalence model is contrasted；
Locating module, the contrast module is carried out after human bioequivalence module contrast, if the image information for obtaining and human body
Identification model is contrasted successfully, carries out first step positioning；
Track forms module, and the track forms the first step of the module based on the locating module and positions, after identification
Human body image information is tracked, and forms the human motion track in three dimensions；
The track is formed direction module, the direction module human motion track and the storage mould that module is formed
The movement locus pre-set in block is contrasted, and determines the direction of human motion track；
Counting module, the counting module counts the stream of people according to the human motion course bearing that the direction module determines
Amount；
Computing module, the entrance flow of the people that the computing module is counted to the counting module and output flow of the people are united
Meter is calculated, and is then analyzed with background system data, is calculated according to sales volume and sale odd number, obtains stream of people's conversion
Rate.
It is further preferred that also include extraction module, in the image information that the extraction module is obtained from the camera,
Human body contour outline is extracted, and transmits the people for extracting the extraction module to the contrast module, the contrast module
Body profile is contrasted with the human bioequivalence model of storage.
It is further preferred that the contrast module by the human body contour outline of extraction and storage human bioequivalence module carry out it is right
Than when, also include to human body contour outline contrast similarity threshold analysis, when human body contour outline with storage human bioequivalence model contrast phase
During like degree higher than threshold value, human body contour outline and human bioequivalence Model Matching success, when human body contour outline and the human bioequivalence module of storage
When contrast similarity is less than threshold value, human body contour outline fails with human bioequivalence Model Matching, it is impossible to the figure for obtaining the camera
As definition is people.
It is further preferred that the track forms module is defined as X by approach axis, direction of going out is defined as Y, passes through
The locating module is carried out after first step positioning, respectively decreasing or increasing calculating by the track in X, Y both direction
To motion track.
It is further preferred that the track forms module also carries out smoothness analysis to human motion track, judge smooth
Whether degree meets the threshold value of advance self-defined track, if it is satisfied, retaining human motion track, if be unsatisfactory for, abandons people
Body motion track.
It is further preferred that also including scene partitioning module, the scene partitioning module is entered to the detection zone in image
Row scene partitioning, by scene partitioning, obtains the excursion of human body image size in detection zone.
It is further preferred that the computing module forms form for people flow rate statistical situation, according to form subsequent analysis
Shop operation situation.
The invention has the beneficial effects as follows:
The system of the present invention first sets up in advance manikin, is then contrasted by contrast module, first determines what is obtained
Image is behaved, and reduces the rate of false alarm of system；It is first self-defined to preset a track, motion track is obtained in three dimensions, according to
Track contrasts, and determines that people enters outgoing direction, can accurately recognize someone's turnover, but also can determine direction, and precision is higher.
The system of the present invention can automatic report generation, obtain into passenger flow, go out volume of passenger traffic, the data such as number of times of stopping, and can
To carry out comprehensive analysis with the sales volume on backstage, the sale data such as odd number, the data messages such as volume of the flow of passengers conversion ratio are obtained, to businessman
Analysis shop situation is significant.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, below with presently preferred embodiments of the present invention and coordinate accompanying drawing describe in detail as after.
The specific embodiment of the present invention is shown in detail in by following examples and its accompanying drawing.
Description of the drawings
Technical scheme in order to be illustrated more clearly that embodiment of the present invention technology, below will be in the description of embodiment technology
The required accompanying drawing for using is briefly described, it should be apparent that, drawings in the following description are only some realities of the present invention
Example is applied, for those of ordinary skill in the art, on the premise of not paying creative work, can be with according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is present system schematic diagram.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than the embodiment of whole.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
With reference to shown in Fig. 1, a kind of tracking statistics flow of the people based on video analysis pattern is disclosed in the present embodiment is
System, hardware aspect mainly includes：Camera, storage device, CPU computing devices etc..Functionally include：Memory module, extracts
Module, contrast module, locating module, track forms module, direction module, counting module, computing module, scene partitioning module.
Camera is used to obtain image information, and camera set location is arranged according to concrete scene, deposited in a storage module
The human bioequivalence model that storage pre-builds, and also store the movement locus of advance self-defined setting in memory module；Contrast mould
The image information that block obtains camera is contrasted with the human bioequivalence model of storage in memory module；Before contrast, first
Human body contour outline is extracted, in the image information that extraction module is obtained from camera, human body contour outline is extracted, and passed
Contrast module is transported to, the human body contour outline that contrast module extracts extraction module is contrasted with the human bioequivalence model of storage.
Contrast module also includes to human body when the human body contour outline of extraction is contrasted with the human bioequivalence module of storage
Silhouette contrast similarity threshold is analyzed, when human body contour outline is higher than threshold value with the human bioequivalence model contrast similarity of storage, people
Body profile and human bioequivalence Model Matching success, when human body contour outline is less than threshold value with the human bioequivalence module contrast similarity of storage
When, human body contour outline fails with human bioequivalence Model Matching, it is impossible to which the image definition for obtaining camera is behaved.
Contrast module is carried out after human bioequivalence module contrast, if the image information for obtaining is contrasted into human bioequivalence model
Work(, carries out first step positioning；Track forms the first step of the module based on locating module and positions, to the human body image information after identification
It is tracked, forms the human motion track in three dimensions.
Specifically, track forms module and approach axis is defined as into X, and direction of going out is defined as Y, is entered by locating module
After row first step positioning, decreasing or increasing being calculated motion track by the track in X, Y both direction respectively.
Track forms module and also carries out smoothness analysis to human motion track, judges whether smoothness meets and makes by oneself in advance
The threshold value of adopted track, if it is satisfied, retaining human motion track, if be unsatisfactory for, abandons human motion track.
The motion rail that direction module will pre-set in the human motion track of track formation module formation and memory module
Mark is contrasted, and determines the direction of human motion track；Then the human motion track side that counting module determines according to direction module
To statistics flow of the people；The entrance flow of the people and output flow of the people that computing module is counted to counting module carries out statistical computation, then
It is analyzed with background system data, is calculated according to sales volume and sale odd number, obtains stream of people's conversion ratio.Computing module pin
Form is formed to people flow rate statistical situation, according to form subsequent analysis shop operation situation.
In the present embodiment, scene partitioning module carries out scene partitioning to the detection zone in image, by scene partitioning,
Obtain the excursion of human body image size in detection zone.
Principle in the present embodiment：
The human bioequivalence model for first pre-building and the movement locus of self-defined setting, camera is in scene division module
Human body image is obtained, then human body contour outline is extracted, in the image information that extraction module is obtained from camera, by human body wheel
Exterior feature is extracted, and is transmitted to contrast module, and the human body contour outline that contrast module extracts extraction module is known with the human body of storage
Other model is contrasted when human body contour outline is higher than threshold value with the human bioequivalence model contrast similarity of storage, human body contour outline and people
The match is successful for body identification model, when human body contour outline is less than threshold value with the human bioequivalence module contrast similarity of storage, human body wheel
It is wide to fail with human bioequivalence Model Matching, it is impossible to which that the image definition for obtaining camera is behaved；Contrast module carries out human bioequivalence
After module contrast, if the image information for obtaining is contrasted successfully with human bioequivalence model, first step positioning is carried out；Track forms mould
The first step of the block based on locating module is positioned, and the human body image information after identification is tracked, and forms the people in three dimensions
Body motion track；Smoothness analysis is carried out to human motion track, judges whether smoothness meets the threshold of advance self-defined track
Value, if it is satisfied, retaining human motion track, if be unsatisfactory for, abandons human motion track；Direction module forms track
The movement locus pre-set in human motion track and memory module that module is formed is contrasted, and determines human motion track
Direction；Then counting module counts flow of the people according to the human motion course bearing that direction module determines.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or using the present invention.
Various modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, the present invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope for causing.
Claims (7)
1. the system that a kind of tracking based on Video Analysis Technology counts flow of the people, it is characterised in that it includes：
Camera, the camera obtains image information；
Memory module, the human bioequivalence model that the memory module storage pre-builds, the memory module also store it is advance from
The movement locus that definition is arranged；
The human body stored in contrast module, the image information that the contrast module obtains the camera and the memory module
Identification model is contrasted；
Locating module, the contrast module is carried out after human bioequivalence module contrast, if the image information for obtaining and human bioequivalence
Model is contrasted successfully, carries out first step positioning；
Track forms module, and the track forms the first step of the module based on the locating module and positions, to the human body after identification
Image information is tracked, and forms the human motion track in three dimensions；
Direction module, the direction module forms the track in human motion track and the memory module that module is formed
The movement locus for pre-setting is contrasted, and determines the direction of human motion track；
Counting module, the counting module counts flow of the people according to the human motion course bearing that the direction module determines；
Computing module, the entrance flow of the people that the computing module is counted to the counting module and output flow of the people carry out statistics meter
Calculate, be then analyzed with background system data, calculated according to sales volume and sale odd number, obtain stream of people's conversion ratio.
2. the system that a kind of tracking based on Video Analysis Technology according to claim 1 counts flow of the people, its feature exists
In also including extraction module, in the image information that the extraction module is obtained from the camera, human body contour outline being extracted
Come, and transmit to the contrast module, the human body contour outline that the contrast module extracts the extraction module and the people for storing
Body identification model is contrasted.
3. the system that a kind of tracking based on Video Analysis Technology according to claim 2 counts flow of the people, its feature exists
In the contrast module also includes to human body when the human body contour outline of extraction is contrasted with the human bioequivalence module of storage
Silhouette contrast similarity threshold is analyzed, when human body contour outline is higher than threshold value with the human bioequivalence model contrast similarity of storage, people
Body profile and human bioequivalence Model Matching success, when human body contour outline is less than threshold value with the human bioequivalence module contrast similarity of storage
When, human body contour outline fails with human bioequivalence Model Matching, it is impossible to which the image definition for obtaining the camera is behaved.
4. the system that a kind of tracking based on Video Analysis Technology according to claim 1 counts flow of the people, its feature exists
In the track forms module and approach axis are defined as into X, and direction of going out is defined as Y, and by the locating module the is carried out
After one step positioning, decreasing or increasing being calculated motion track by the track in X, Y both direction respectively.
5. the system that a kind of tracking based on Video Analysis Technology according to claim 4 counts flow of the people, its feature exists
In the track forms module and also carries out smoothness analysis to human motion track, judges whether smoothness meets and makes by oneself in advance
The threshold value of adopted track, if it is satisfied, retaining human motion track, if be unsatisfactory for, abandons human motion track.
6. the system that a kind of tracking based on Video Analysis Technology according to claim 1 counts flow of the people, its feature exists
In also including scene partitioning module, the scene partitioning module carries out scene partitioning to the detection zone in image, by scene
Divide, obtain the excursion of human body image size in detection zone.
7. the system that a kind of tracking based on Video Analysis Technology according to claim 1 counts flow of the people, its feature exists
In the computing module forms form for people flow rate statistical situation, according to form subsequent analysis shop operation situation.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611256466.3A CN106650695A (en) | 2016-12-30 | 2016-12-30 | Video analysis technology-based people flow tracking statistics system |
| PCT/CN2017/111929 WO2018121127A1 (en) | 2016-12-30 | 2017-11-20 | System for collecting statistics on pedestrian traffic by means of tracking based on video analysis technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611256466.3A CN106650695A (en) | 2016-12-30 | 2016-12-30 | Video analysis technology-based people flow tracking statistics system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106650695A true CN106650695A (en) | 2017-05-10 |
Family
ID=58838572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611256466.3A Pending CN106650695A (en) | 2016-12-30 | 2016-12-30 | Video analysis technology-based people flow tracking statistics system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106650695A (en) |
| WO (1) | WO2018121127A1 (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358163A (en) * | 2017-06-14 | 2017-11-17 | 广东数相智能科技有限公司 | Visitor's line trace statistical method, electronic equipment and storage medium based on recognition of face |
| CN108090454A (en) * | 2017-12-26 | 2018-05-29 | 上海理工大学 | Campus bathhouse people flow rate statistical system |
| WO2018121127A1 (en) * | 2016-12-30 | 2018-07-05 | 苏州万店掌网络科技有限公司 | System for collecting statistics on pedestrian traffic by means of tracking based on video analysis technique |
| CN108833420A (en) * | 2018-06-23 | 2018-11-16 | 苏州万店掌网络科技有限公司 | A kind of system based on video analysis and wifi probe combinations analysis passenger flow |
| CN108875677A (en) * | 2018-06-29 | 2018-11-23 | 上海小蚁科技有限公司 | Passenger flow volume statistical method and device, storage medium, terminal |
| CN109902551A (en) * | 2018-11-09 | 2019-06-18 | 阿里巴巴集团控股有限公司 | The real-time stream of people's statistical method and device of open scene |
| CN110659578A (en) * | 2019-08-26 | 2020-01-07 | 中国电子科技集团公司电子科学研究院 | Passenger flow statistical method, system and equipment based on detection and tracking technology |
| CN112001941A (en) * | 2020-06-05 | 2020-11-27 | 成都睿畜电子科技有限公司 | Piglet supervision method and system based on computer vision |
| CN112580397A (en) * | 2019-09-29 | 2021-03-30 | 北京市商汤科技开发有限公司 | Data processing method, device and storage medium |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN113369796A (en) * | 2021-05-26 | 2021-09-10 | 上海御建装饰设计工程有限公司 | Intelligent automatic tracking and monitoring system for cultural relic restoration |
| CN113743324A (en) * | 2021-09-07 | 2021-12-03 | 易科捷(武汉)生态科技有限公司成都分公司 | Automatic updating type fish identification system based on Internet of things |
| JP2022503373A (en) * | 2019-09-29 | 2022-01-12 | 北京市商▲湯▼科技▲開▼▲發▼有限公司 | Data processing methods, devices and storage media |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109583411B (en) * | 2018-12-09 | 2022-10-21 | 大连海事大学 | TOF camera-based tourist category online auditing method |
| CN110175562B (en) * | 2019-05-24 | 2024-01-16 | 深圳职业技术大学 | Parallel computing-based gpu acceleration pedestrian detection algorithm |
| CN113051975B (en) * | 2019-12-27 | 2024-04-02 | 深圳云天励飞技术有限公司 | People flow statistics method and related products |
| CN111860261B (en) * | 2020-07-10 | 2023-11-03 | 北京猎户星空科技有限公司 | Passenger flow value statistical method, device, equipment and medium |
| CN111914754B (en) * | 2020-08-03 | 2023-06-30 | 杭州云栖智慧视通科技有限公司 | Image content similarity measurement method and device and computer equipment |
| CN113326830B (en) * | 2021-08-04 | 2021-11-30 | 北京文安智能技术股份有限公司 | Passenger flow statistical model training method and passenger flow statistical method based on overlook images |
| CN115215177B (en) * | 2022-08-26 | 2023-06-16 | 中建八局发展建设有限公司 | Intelligent elevator lifting identification system and method |
| CN116542858B (en) * | 2023-07-03 | 2023-09-05 | 众芯汉创(江苏)科技有限公司 | Data splicing analysis system based on space track |
| CN117226843B (en) * | 2023-09-27 | 2024-02-27 | 盐城工学院 | Robot movement track control method and system based on visual servo |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101587539A (en) * | 2008-05-21 | 2009-11-25 | 上海新联纬讯科技发展有限公司 | Method and system of population flow statistics based on intelligent video identification technology |
| CN101739653A (en) * | 2008-11-13 | 2010-06-16 | 上海汇纳网络信息科技有限公司 | Passenger flow analysis system |
| CN102982598A (en) * | 2012-11-14 | 2013-03-20 | 三峡大学 | Video people counting method and system based on single camera scene configuration |
| CN103093274A (en) * | 2012-12-30 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Pedestrian counting method based on video |
| US20160019698A1 (en) * | 2014-07-21 | 2016-01-21 | Florida Atlantic University | Systems and methods for people counting in sequential images |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19962201A1 (en) * | 1999-09-06 | 2001-03-15 | Holger Lausch | Determination of people activity within a reception area using cameras and sensors |
| US7987111B1 (en) * | 2006-10-30 | 2011-07-26 | Videomining Corporation | Method and system for characterizing physical retail spaces by determining the demographic composition of people in the physical retail spaces utilizing video image analysis |
| CN101937534A (en) * | 2010-09-17 | 2011-01-05 | 上海沐盈信息科技有限公司 | Electronic marketing management system and management method |
| CN202374374U (en) * | 2011-10-25 | 2012-08-08 | 武汉金数字图像信号设备有限公司 | Shopping mall crowd flow dynamic management system based on remote images |
| CN102750539B (en) * | 2012-06-06 | 2016-05-18 | 深圳市海亿达能源科技股份有限公司 | A kind of device that regional space crowd is added up and statistical method thereof |
| CN103425967B (en) * | 2013-07-21 | 2016-06-01 | 浙江大学 | A kind of based on stream of people's monitoring method of pedestrian detection and tracking |
| CN106650695A (en) * | 2016-12-30 | 2017-05-10 | 苏州万店掌网络科技有限公司 | Video analysis technology-based people flow tracking statistics system |
-
2016
- 2016-12-30 CN CN201611256466.3A patent/CN106650695A/en active Pending
-
2017
- 2017-11-20 WO PCT/CN2017/111929 patent/WO2018121127A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101587539A (en) * | 2008-05-21 | 2009-11-25 | 上海新联纬讯科技发展有限公司 | Method and system of population flow statistics based on intelligent video identification technology |
| CN101739653A (en) * | 2008-11-13 | 2010-06-16 | 上海汇纳网络信息科技有限公司 | Passenger flow analysis system |
| CN102982598A (en) * | 2012-11-14 | 2013-03-20 | 三峡大学 | Video people counting method and system based on single camera scene configuration |
| CN103093274A (en) * | 2012-12-30 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Pedestrian counting method based on video |
| US20160019698A1 (en) * | 2014-07-21 | 2016-01-21 | Florida Atlantic University | Systems and methods for people counting in sequential images |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018121127A1 (en) * | 2016-12-30 | 2018-07-05 | 苏州万店掌网络科技有限公司 | System for collecting statistics on pedestrian traffic by means of tracking based on video analysis technique |
| CN107358163A (en) * | 2017-06-14 | 2017-11-17 | 广东数相智能科技有限公司 | Visitor's line trace statistical method, electronic equipment and storage medium based on recognition of face |
| CN108090454A (en) * | 2017-12-26 | 2018-05-29 | 上海理工大学 | Campus bathhouse people flow rate statistical system |
| CN108833420A (en) * | 2018-06-23 | 2018-11-16 | 苏州万店掌网络科技有限公司 | A kind of system based on video analysis and wifi probe combinations analysis passenger flow |
| CN108875677A (en) * | 2018-06-29 | 2018-11-23 | 上海小蚁科技有限公司 | Passenger flow volume statistical method and device, storage medium, terminal |
| CN108875677B (en) * | 2018-06-29 | 2020-11-17 | 上海小蚁科技有限公司 | Passenger flow volume statistical method and device, storage medium and terminal |
| CN109902551A (en) * | 2018-11-09 | 2019-06-18 | 阿里巴巴集团控股有限公司 | The real-time stream of people's statistical method and device of open scene |
| CN110659578A (en) * | 2019-08-26 | 2020-01-07 | 中国电子科技集团公司电子科学研究院 | Passenger flow statistical method, system and equipment based on detection and tracking technology |
| WO2021057149A1 (en) * | 2019-09-29 | 2021-04-01 | 北京市商汤科技开发有限公司 | Data processing method and apparatus, and storage medium |
| CN112580397A (en) * | 2019-09-29 | 2021-03-30 | 北京市商汤科技开发有限公司 | Data processing method, device and storage medium |
| TWI745101B (en) * | 2019-09-29 | 2021-11-01 | 大陸商北京市商湯科技開發有限公司 | Data processing method, apparatuses, and computer readable recording media |
| JP2022503373A (en) * | 2019-09-29 | 2022-01-12 | 北京市商▲湯▼科技▲開▼▲發▼有限公司 | Data processing methods, devices and storage media |
| US11335098B2 (en) * | 2019-09-29 | 2022-05-17 | Beijing Sensetime Technology Development Co., Ltd. | Data processing methods, apparatuses and storage media |
| CN112001941A (en) * | 2020-06-05 | 2020-11-27 | 成都睿畜电子科技有限公司 | Piglet supervision method and system based on computer vision |
| CN112001941B (en) * | 2020-06-05 | 2023-11-03 | 成都睿畜电子科技有限公司 | Piglet supervision method and system based on computer vision |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN112668525B (en) * | 2020-12-31 | 2024-05-07 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN113369796A (en) * | 2021-05-26 | 2021-09-10 | 上海御建装饰设计工程有限公司 | Intelligent automatic tracking and monitoring system for cultural relic restoration |
| CN113743324A (en) * | 2021-09-07 | 2021-12-03 | 易科捷(武汉)生态科技有限公司成都分公司 | Automatic updating type fish identification system based on Internet of things |
| CN113743324B (en) * | 2021-09-07 | 2022-10-18 | 易科捷(武汉)生态科技有限公司成都分公司 | Automatic updating type fish identification system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018121127A1 (en) | 2018-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106650695A (en) | Video analysis technology-based people flow tracking statistics system | |
| CA3094424C (en) | Safety monitoring and early-warning method for man-machine interaction behavior of underground conveyor belt operator | |
| CN103871078B (en) | A kind of billiard ball batting key message detection method and system | |
| WO2020253308A1 (en) | Human-machine interaction behavior security monitoring and forewarning method for underground belt transportation-related personnel | |
| US7409076B2 (en) | Methods and apparatus for automatically tracking moving entities entering and exiting a specified region | |
| CN110472496A (en) | A kind of traffic video intelligent analysis method based on object detecting and tracking | |
| Porikli | Trajectory distance metric using hidden markov model based representation | |
| CN109344690B (en) | People counting method based on depth camera | |
| CN105844234A (en) | People counting method and device based on head shoulder detection | |
| CN104835323B (en) | Multi-target public transport passenger flow detection method combining with electronic fence | |
| CN103310444B (en) | A kind of method of the monitoring people counting based on overhead camera head | |
| CN105424026A (en) | Indoor navigation and localization method and system based on point cloud tracks | |
| CN103646253A (en) | Bus passenger flow statistics method based on multi-motion passenger behavior analysis | |
| CN104268506A (en) | Passenger flow counting detection method based on depth images | |
| CN106372570A (en) | Visitor flowrate statistic method | |
| CN108376406A (en) | A kind of Dynamic Recurrent modeling and fusion tracking method for channel blockage differentiation | |
| CN105139425A (en) | People counting method and device | |
| CN103646254B (en) | High-density pedestrian detection method | |
| CN106682573B (en) | A kind of pedestrian tracting method of single camera | |
| CN111209781B (en) | Method and device for counting indoor people | |
| CN105184274A (en) | Method of obtaining passenger flow velocity and density parameters based on depth image | |
| CN104183142A (en) | Traffic flow statistics method based on image visual processing technology | |
| CN104778727A (en) | Floating car counting method based on video monitoring processing technology | |
| Zaki et al. | Automated analysis of pedestrians’ nonconforming behavior and data collection at an urban crossing | |
| CN102855508A (en) | Opening type campus anti-following system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |