CN106548158A - Crowd density intelligent monitor system and method based on machine vision - Google Patents
Crowd density intelligent monitor system and method based on machine vision Download PDFInfo
- Publication number
- CN106548158A CN106548158A CN201610975962.8A CN201610975962A CN106548158A CN 106548158 A CN106548158 A CN 106548158A CN 201610975962 A CN201610975962 A CN 201610975962A CN 106548158 A CN106548158 A CN 106548158A
- Authority
- CN
- China
- Prior art keywords
- crowd
- video information
- density
- crowd density
- machine vision
- 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
Abstract
The present invention provides a kind of crowd density intelligent monitor system and method based on machine vision, crowd density intelligent monitor system includes photographic head, embedded device and the computer client being sequentially connected, wherein, the photographic head is used for Real-time Collection crowd video information and sends to embedded device；The embedded device is used to extract video information and be analyzed process, and result is sent to computer client；The computer client is used to judge whether population density is in security interval and uploads real-time crowd's video information of collection to server, and is locally being shown.The present invention under the detection of intelligentized detecting system, can real-time monitoring crowd density exactly, low cost, degree of accuracy be high, excessive in population density and exceed certain threshold values and when produce potential danger, can realize Realtime Alerts.
Description
Technical field
The present invention relates to intelligentized crowd density analysis field, more particularly to a kind of crowd density based on machine vision
Intelligent monitor system and method.
Background technology
Vision is the topmost means that the mankind obtain information from the Nature, and machine vision is that artificial intelligence is quick
One branch of development.In brief, machine vision is exactly to replace human eye to measure and judge with machine.Moving object detection
It is the hot issue of field of machine vision with tracking, obtains the kinematic parameter of moving target, such as position, speed, acceleration etc., with
And movement locus, so as to being further processed and analyzing, the behavior understanding to moving target is realized, it is more higher leveled to complete
Task.
Traditional manual monitoring system does not break away from high cost, the big shortcoming of the low error of precision.In actual life, in order to obtain
Accurate crowd's data on flows is obtained, generally using the method for artificial counting, but this method is suffered from the drawback that：First, people
Group is that dynamic flows, and the flow of the people of certain time period can not represent the flow of the people of all times, have on Annual distribution
Limitation；Secondly, when crowd density is larger, the error counted using artificial visual is very big, in actual count analysis
Value it is extremely limited.With scientific statistics analysis and computer technology continuous development, demographics oneself initially enter automatically
In the change stage, using advanced Video Supervision Technique, obtain instant, reliable crowd's information and have become possibility.
The content of the invention
In order to overcome the shortcoming that prior art is present with a kind of not enough, crowd density based on machine vision of present invention offer
Intelligent monitor system and method, under the detection of intelligentized detecting system, can real-time monitoring crowd density exactly, cost
Low, degree of accuracy is high, excessive in population density and exceed certain threshold values and when produce potential danger, can realize report in real time
It is alert.
To solve above-mentioned technical problem, the present invention provides following technical scheme：A kind of crowd density based on machine vision
Intelligent monitor system, including the photographic head, embedded device and computer client that are sequentially connected, wherein
The photographic head is used for Real-time Collection crowd video information and is sent to embedded device；
The embedded device is used to extract video information and be analyzed process, and result is sent to computer
Client；
Whether the computer client is used to judge population density in security interval and the real-time crowd of upload collection
Video information is to server, and is locally being shown.
Further, the embedded device connects the computer client by wired or WIFI wireless telecommunications.
It is another object of the invention to provide a kind of crowd density intelligent monitoring method based on machine vision, including with
Lower step：
S1, photographic head Real-time Collection simultaneously read video information, and video information is sent to embedded device；
S2, embedded device extract video information and are analyzed process, and result is sent to computer clients
End；
According to result is received to obtain, S3, computer client judge whether population density is in security interval, if so,
Then return to step S1；If it is not, then producing alarm signal；
The real-time crowd's video information for gathering is uploaded onto the server by S4, computer client, and is locally being shown.
Further, in step S2, embedded device extracts video information, and which is specially：
Video information is processed using average background modeling, obtain monitored picture background；By current monitor picture
Subtracting background, obtains Target Photo；Gray processing, binaryzation and normalization are carried out to Target Photo.
Further, process is analyzed to video information in step S2, which is specifically divided into：Video information is carried out
Demographics and crowd density analysis, wherein
The demographics are：The target group moved in detecting Target Photo, and by target group from Target Photo
In extract；The motion of tracking target group；Finally counted；
The crowd density is analyzed：According to demographics result, crowd is analyzed in the regional extent of Target Photo close
Degree.
Further, analyzed by the crowd density, by video information be divided into relatively low density scene, low-density scene,
Intensive scene, comparatively dense scene and blocking scene, wherein the crowd of intensive scene, comparatively dense scene and blocking scene is intensive people
Group, the computer client send different alarms according to different dense population scenes.
After above-mentioned technical proposal, the present invention at least has the advantages that：
1st, the present inventor's population density intelligent monitor system is capable of the number in certain region of dynamic detection, and number record is than tradition
Statistical method precision degree it is high, low cost；
2nd, the population density in the present inventor's population density intelligent monitor system energy real-time monitoring block region, video monitoring regional
Population density it is excessive more than certain threshold values produce potential danger when, Realtime Alerts can be realized.
Description of the drawings
Fig. 1 is structural representation of the present invention based on the crowd density intelligent monitor system of machine vision；
Fig. 2 is flow chart of the present invention based on the crowd density intelligent monitoring method of machine vision；
Fig. 3 is video demographics schematic diagram of the present invention based on the crowd density intelligent monitoring method of machine vision；
Fig. 4 is crowd density analysis principle figure of the present invention based on the crowd density intelligent monitoring method of machine vision.
Specific embodiment
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combine, the application is described in further detail with specific embodiment below in conjunction with the accompanying drawings.
As described in Figure 1, the present invention provides a kind of crowd density intelligent monitor system based on machine vision, including one is taken the photograph
As head, an embedded device based on Arm frameworks, a computer, computer install relative clients end, you can complete whole system
Build, it is more more intelligent than traditional video monitoring system.Preferably, between embedded device and computer can by wired or
WIFI wireless telecommunications connect.
Computer client uses Qt as development environment, and Qt is used by a cross-platform C++ figures that Trolltech is developed
Family interface application Development Framework.Qt can provide numerous graphic user interface development modules to application developer,
Cover almost all of interface development function.The warning information from embedded device can be captured and alarm signal is produced
Number, and the video of its upload in real time, and locally shown.
As described in Figure 2, the system carries out intellectual monitoring to crowd density by the following method：
S1, photographic head Real-time Collection simultaneously read video information, and video information is sent to embedded device；
S2, embedded device extract video information and are analyzed process, and result is sent to computer clients
End；
According to result is received to obtain, S3, computer client judge whether population density is in security interval, if so,
Then return to step S1；If it is not, then producing alarm signal；
The real-time crowd's video information for gathering is uploaded onto the server by S4, computer client, and is locally being shown.
Fig. 3 is the video demographics schematic diagram based on machine vision, first obtains monitored picture with average background modeling
Background, input video series, then by current picture subtracting background, obtains the target area in picture；Further picture is entered
Row gray processing, binaryzation and normalization, then carry out a few wheel target detections, and after target leaves region, total number of persons subtracts one, enter
Region just adds one, is finally counted；And it is to count the number in current video picture to count.
Fig. 4 is the crowd density analysis principle figure based on machine vision, mainly includes the content of two aspects：Monitor video
In real-time demographics and crowd density classification, input video series, wherein crowd density analyze by following four part group
Into：Foreground extraction, the perspective analysis of pixel weighting process, demographics, four parts of listener clustering：Foreground extraction is will be current
Frame carries out extraction of the differential comparison realization to foreground image with background frames, wherein it is considered as prospect to distinguish larger pixel region
Region, and it is considered as then background area to distinguish less pixel region；Fixed background extraction method must first obtain background image,
And background image can be automatically updated with the change of illumination and external environment condition；The perspective analysis of scene is pith.By
In there is scene perspective phenomenon, human body size in the picture is got over from photographic head with far and near and different with a distance from photographic head
It is remote then human body is less, on the contrary it is bigger.In order to obtain the accurate crowd density of scene it is necessary to each pixel in scene
It is weighted process.Demographics are counted to region crowd.Listener clustering is i.e. to the crowd's classifying system pair in sample
Crowd density is differentiated.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
It is understood by, can these embodiments be carried out with various equivalent changes without departing from the principles and spirit of the present invention
Change, change, replace and modification, the scope of the present invention is limited by claims and its equivalency range.
Claims (6)
1. a kind of crowd density intelligent monitor system based on machine vision, it is characterised in that including the photographic head being sequentially connected,
Embedded device and computer client, wherein
The photographic head is used for Real-time Collection crowd video information and sends to embedded device；
The embedded device is used to extract video information and be analyzed process, and result is sent to computer clients
End；
Whether the computer client is used to judge population density in security interval and real-time crowd's video of upload collection
Information is to server, and is locally being shown.
2. the crowd density intelligent monitor system based on machine vision according to claim 1, it is characterised in that described embedding
Enter formula equipment and connect the computer client by wired or WIFI wireless telecommunications.
3. a kind of crowd density intelligent monitoring method based on machine vision, it is characterised in that comprise the following steps：
S1, photographic head Real-time Collection simultaneously read video information, and video information is sent to embedded device；
S2, embedded device extract video information and are analyzed process, and result is sent to computer client；
According to result is received to obtain, S3, computer client judge that population density, whether in security interval, is if so, then returned
Return step S1；If it is not, then producing alarm signal；
The real-time crowd's video information for gathering is uploaded onto the server by S4, computer client, and is locally being shown.
4. the crowd density intelligent monitoring method based on machine vision according to claim 3, it is characterised in that the step
In rapid S2, embedded device extracts video information, and which is specially：
Video information is processed using average background modeling, obtain monitored picture background；Current monitor picture is deducted
Background, obtains Target Photo；Gray processing, binaryzation and normalization are carried out to Target Photo.
5. the crowd density intelligent monitoring method based on machine vision according to claim 4, it is characterised in that the step
Process is analyzed to video information in rapid S2, which is specifically divided into：Demographics and crowd density analysis are carried out to video information,
Wherein
The demographics are：The target group moved in detecting Target Photo, and target group is carried from Target Photo
Take out；The motion of tracking target group；Finally counted；
The crowd density is analyzed：According to demographics result, crowd density is analyzed in the regional extent of Target Photo.
6. the crowd density intelligent monitoring method based on machine vision according to claim 5, it is characterised in that by institute
Crowd density analysis is stated, video information is divided into into relatively low density scene, low-density scene, intensive scene, comparatively dense scene and is blocked up
Plug scene, wherein intensive scene, comparatively dense scene and blocking scene crowd be dense population, the computer client according to
Different dense population scenes send different alarms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610975962.8A CN106548158A (en) | 2016-11-07 | 2016-11-07 | Crowd density intelligent monitor system and method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610975962.8A CN106548158A (en) | 2016-11-07 | 2016-11-07 | Crowd density intelligent monitor system and method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106548158A true CN106548158A (en) | 2017-03-29 |
Family
ID=58394294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610975962.8A Pending CN106548158A (en) | 2016-11-07 | 2016-11-07 | Crowd density intelligent monitor system and method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106548158A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109632265A (en) * | 2019-01-28 | 2019-04-16 | 上海大学 | A kind of the unmanned boat water sampling device mated condition detection system and method for view-based access control model |
| CN110942045A (en) * | 2019-12-05 | 2020-03-31 | 安徽信息工程学院 | Intelligent fish tank feeding system based on machine vision |
| CN111724442A (en) * | 2020-05-28 | 2020-09-29 | 上海商汤智能科技有限公司 | Image processing method and device, electronic device and storage medium |
| CN113111777A (en) * | 2021-04-12 | 2021-07-13 | 国网吉林省电力有限公司四平供电公司 | Indoor personnel density detection system and detection method based on ARM platform |
| CN113642362A (en) * | 2020-05-11 | 2021-11-12 | 广东毓秀科技有限公司 | Crowd density estimation method for intelligent escape in dense place |
| CN113642403A (en) * | 2021-07-13 | 2021-11-12 | 重庆科技学院 | Crowd abnormal intelligent safety detection system based on edge calculation |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101325690A (en) * | 2007-06-12 | 2008-12-17 | 上海正电科技发展有限公司 | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow |
| CN101607668A (en) * | 2008-06-17 | 2009-12-23 | 上海阿艾依智控系统有限公司 | Embedded computer vision escalator pedestrian flow supervision and alarm device |
| CN101959060A (en) * | 2010-10-26 | 2011-01-26 | 镇江科大船苑计算机网络工程有限公司 | Video passenger flow monitoring system and method |
| CN103164711A (en) * | 2013-02-25 | 2013-06-19 | 昆山南邮智能科技有限公司 | Regional people stream density estimation method based on pixels and support vector machine (SVM) |
| CN103824074A (en) * | 2014-01-26 | 2014-05-28 | 中山大学 | Crowd density estimation method based on background subtraction and texture features and system |
| CN104616432A (en) * | 2015-02-04 | 2015-05-13 | 田文华 | Intelligent identification and control method and system for people flow density |
| CN105791774A (en) * | 2016-03-31 | 2016-07-20 | 北京工业大学 | Surveillance video transmission method based on video content analysis |
-
2016
- 2016-11-07 CN CN201610975962.8A patent/CN106548158A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101325690A (en) * | 2007-06-12 | 2008-12-17 | 上海正电科技发展有限公司 | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow |
| CN101607668A (en) * | 2008-06-17 | 2009-12-23 | 上海阿艾依智控系统有限公司 | Embedded computer vision escalator pedestrian flow supervision and alarm device |
| CN101959060A (en) * | 2010-10-26 | 2011-01-26 | 镇江科大船苑计算机网络工程有限公司 | Video passenger flow monitoring system and method |
| CN103164711A (en) * | 2013-02-25 | 2013-06-19 | 昆山南邮智能科技有限公司 | Regional people stream density estimation method based on pixels and support vector machine (SVM) |
| CN103824074A (en) * | 2014-01-26 | 2014-05-28 | 中山大学 | Crowd density estimation method based on background subtraction and texture features and system |
| CN104616432A (en) * | 2015-02-04 | 2015-05-13 | 田文华 | Intelligent identification and control method and system for people flow density |
| CN105791774A (en) * | 2016-03-31 | 2016-07-20 | 北京工业大学 | Surveillance video transmission method based on video content analysis |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109632265A (en) * | 2019-01-28 | 2019-04-16 | 上海大学 | A kind of the unmanned boat water sampling device mated condition detection system and method for view-based access control model |
| CN109632265B (en) * | 2019-01-28 | 2020-01-31 | 上海大学 | System and method for detecting butting state of unmanned boat water collecting devices based on vision |
| CN110942045A (en) * | 2019-12-05 | 2020-03-31 | 安徽信息工程学院 | Intelligent fish tank feeding system based on machine vision |
| CN110942045B (en) * | 2019-12-05 | 2023-05-26 | 安徽信息工程学院 | Intelligent fish tank feeding system based on machine vision |
| CN113642362A (en) * | 2020-05-11 | 2021-11-12 | 广东毓秀科技有限公司 | Crowd density estimation method for intelligent escape in dense place |
| CN111724442A (en) * | 2020-05-28 | 2020-09-29 | 上海商汤智能科技有限公司 | Image processing method and device, electronic device and storage medium |
| CN113111777A (en) * | 2021-04-12 | 2021-07-13 | 国网吉林省电力有限公司四平供电公司 | Indoor personnel density detection system and detection method based on ARM platform |
| CN113642403A (en) * | 2021-07-13 | 2021-11-12 | 重庆科技学院 | Crowd abnormal intelligent safety detection system based on edge calculation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106548158A (en) | Crowd density intelligent monitor system and method based on machine vision | |
| CN104123544B (en) | Anomaly detection method and system based on video analysis | |
| CN109117827A (en) | Work clothes work hat wearing state automatic identifying method and alarm system based on video | |
| KR101571277B1 (en) | Apparatus and Method of Classifying Movement of Objects in a Monitoring Zone | |
| CN106571014A (en) | Method for identifying abnormal motion in video and system thereof | |
| CN104036236B (en) | A kind of face gender identification method based on multiparameter exponential weighting | |
| CN108629316A (en) | A kind of video accident detection method of various visual angles | |
| CN105426820B (en) | More people's anomaly detection methods based on safety monitoring video data | |
| CN107622258A (en) | A kind of rapid pedestrian detection method of combination static state low-level image feature and movable information | |
| CN106228709B (en) | A kind of wisdom gold eyeball identifies that one adds paper money alarm method and device | |
| CN106210634A (en) | A kind of wisdom gold eyeball identification personnel fall down to the ground alarm method and device | |
| CN105516652B (en) | A kind of intelligent campus street lamp illumination system | |
| CN106652291A (en) | Indoor simple monitoring and alarming system and method based on Kinect | |
| CN106127814A (en) | A kind of wisdom gold eyeball identification gathering of people is fought alarm method and device | |
| CN112163572A (en) | Method and device for identifying object | |
| CN104463125A (en) | DSP-based automatic face detecting and tracking device and method | |
| CN110348371A (en) | Human body three-dimensional acts extraction method | |
| CN104899574B (en) | A kind of disengaging event detecting method and system | |
| Iazzi et al. | Fall detection based on posture analysis and support vector machine | |
| CN113963301A (en) | Space-time feature fused video fire and smoke detection method and system | |
| Zambanini et al. | Detecting falls at homes using a network of low-resolution cameras | |
| CN104778676A (en) | Depth ranging-based moving target detection method and system | |
| CN207233038U (en) | Face is called the roll and number system | |
| Belbachir et al. | Event-driven feature analysis in a 4D spatiotemporal representation for ambient assisted living | |
| Huang et al. | A method for fast fall detection |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170329 |