CN110827316A - Crowd panic scatter detection method and system, readable storage medium and electronic equipment - Google Patents
Crowd panic scatter detection method and system, readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN110827316A CN110827316A CN201911036880.7A CN201911036880A CN110827316A CN 110827316 A CN110827316 A CN 110827316A CN 201911036880 A CN201911036880 A CN 201911036880A CN 110827316 A CN110827316 A CN 110827316A
- Authority
- CN
- China
- Prior art keywords
- crowd
- pedestrian
- panic
- calculating
- vector direction
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000011156 evaluation Methods 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 12
- 208000019906 panic disease Diseases 0.000 claims description 8
- 108010014172 Factor V Proteins 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 239000000843 powder Substances 0.000 abstract 1
- 230000035945 sensitivity Effects 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a crowd panic four-powder detection method, which comprises the following steps: detecting a moving target of the real-time video stream to obtain a moving track of each pedestrian in the crowd; calculating the speed factor of the crowd; solving the vector direction information entropy of the crowd; evaluating the crowd chaos degree index; and when the crowd confusion degree evaluation index is larger than a preset threshold value, carrying out crowd panic four-dispersing abnormity early warning. According to the invention, the pedestrian movement track is obtained through moving target detection, the crowd speed factor and the vector direction information entropy are obtained according to the pedestrian movement track, and then the crowd chaos degree evaluation index is obtained. The invention also discloses a crowd panic scatter detection system, a readable storage medium and electronic equipment.
Description
Technical Field
The invention relates to the technical field of safety monitoring, in particular to a crowd panic four-dispersing detection method and system, a readable storage medium and electronic equipment.
Background
With the dramatic increase in urban population density, many public infrastructures are often facing short term peak traffic. Global abnormal behaviors (such as abnormal panic of people caused by emergencies and evacuation) which can exist in group movement have great safety hazards. Therefore, it is necessary to detect the abnormal panic and the scattering of the crowd in the public infrastructure and to perform the follow-up treatment in a targeted manner.
The traditional people panic four-scattered detection usually adopts a manual monitoring method, wastes time and labor, and cannot ensure the detection precision, efficiency and sensitivity.
Disclosure of Invention
The invention provides a crowd panic scatter detection method, a crowd panic scatter detection system, a readable storage medium and electronic equipment based on the problems.
The technical scheme for solving the technical problems is as follows: a method for detecting panic and scattering of people comprises the following steps:
s1, acquiring a real-time video stream of a monitoring scene, and carrying out moving target detection on the real-time video stream to obtain a moving track of each pedestrian in a crowd;
s2, calculating a crowd speed factor V according to the motion trail of each pedestrian in the crowdt;
S3, obtaining the crowd vector direction information entropy W according to the motion trail of each pedestrian in the crowdt;
S4, according to the crowd speed factor VtAnd the entropy W of the direction information of the crowd vectortCalculating the crowd chaos degree evaluation index Lt;
S5, evaluating index L when the crowd confusion degreetAnd when the alarm is larger than a preset threshold S, early warning of the panic and the four-dispersing abnormity of the crowd is carried out.
The invention has the beneficial effects that: the real-time video stream is acquired, the moving target is detected to acquire the pedestrian moving track, the crowd speed factor and the vector direction information entropy are acquired according to the pedestrian moving track, the crowd chaos degree evaluation index is further acquired, the crowd panic four-scattered abnormity early warning is automatically performed by utilizing the characteristic that the crowd chaos degree evaluation index is increased when the crowd panic four-scattered, the cost of manually monitoring the crowd panic four-scattered is saved, and the detection precision, efficiency and sensitivity are improved.
The invention also discloses a crowd panic four-dispersing detection system, which comprises:
the motion track acquisition module is used for acquiring a real-time video stream of a monitoring scene, and detecting a motion target of the real-time video stream to obtain a motion track of each pedestrian in a crowd;
the speed factor calculation module is used for calculating a crowd speed factor V according to the motion trail of each pedestrian in the crowdtSaid representative current moment, corresponding to a current frame of said real-time video stream;
the information entropy calculating module is used for calculating the crowd vector direction information entropy W according to the motion trail of each pedestrian in the crowdt;
A chaos degree evaluation index calculation module for calculating the crowd speed factor VtAnd the entropy W of the direction information of the crowd vectortCalculating the crowd chaos degree evaluation index Lt;
An abnormality early warning module for evaluating an index L of the degree of confusion of the populationtAnd when the alarm is larger than a preset threshold S, early warning of the panic and the four-dispersing abnormity of the crowd is carried out.
The invention also provides a readable storage medium, which comprises instructions, and when the instructions are run on the electronic equipment, the electronic equipment is enabled to execute the people panic quartering detection method in the technical scheme.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can be run on the processor, and is characterized in that the processor implements the crowd panic scatter detection method in the technical scheme when executing the program.
According to the technical scheme, the real-time video stream is acquired, the moving target is detected to acquire the pedestrian moving track, the crowd speed factor and the vector direction information entropy are acquired according to the pedestrian moving track, the crowd chaos degree evaluation index is further acquired, the crowd panic four-scattered abnormity early warning is automatically performed by utilizing the characteristic that the crowd chaos degree evaluation index is increased when the crowd panic four-scattered, the cost of manually monitoring the crowd panic four-scattered is saved, and the detection precision, efficiency and sensitivity are improved.
Drawings
Fig. 1 is a flowchart illustrating a method for detecting panic disorder of people according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating 8 region divisions in a crowd panic scatter detection method according to an embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the features of the embodiments of the present invention, i.e., the embodiments, may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flowchart of a crowd panic scatter detection method according to an embodiment of the present invention.
As shown in fig. 1, in this embodiment, a method for detecting a crowd panic scatter includes the following steps:
s1, acquiring a real-time video stream of a monitoring scene, and carrying out moving target detection on the real-time video stream to obtain a moving track of each pedestrian in a crowd;
s2, calculating a crowd speed factor V according to the motion trail of each pedestrian in the crowdt;
S3, according to the movement of each pedestrian in the crowdMoving track, and obtaining the entropy W of the vector direction information of the crowdt;
S4, according to the crowd speed factor VtAnd the entropy W of the direction information of the crowd vectortCalculating the crowd chaos degree evaluation index Lt;
S5, evaluating index L when the crowd confusion degreetAnd when the alarm is larger than a preset threshold S, early warning of the panic and the four-dispersing abnormity of the crowd is carried out.
When the crowd generates panic when meeting an emergency, the crowd generally evacuates in a scattered manner, the average speed of the pedestrians in the crowd changes more rapidly, the vector direction of the pedestrians is more disordered, and meanwhile, the crowd chaos degree evaluation index is also obviously increased. The crowd confusion degree evaluation index threshold value can be preset according to the actual situation, and when the crowd confusion degree evaluation index threshold value is larger than the preset threshold value, the crowd panic four-scattered abnormity early warning is judged.
In the embodiment, the real-time video stream is acquired, the moving target is detected to acquire the pedestrian moving track, the crowd speed factor and the vector direction information entropy are acquired according to the pedestrian moving track, the crowd chaos degree evaluation index is further acquired, meanwhile, the crowd panic four-scattered abnormity early warning is automatically performed by utilizing the characteristic that the crowd chaos degree evaluation index is increased when the crowd panic four-scattered, the cost of manually monitoring the crowd panic four-scattered is saved, and the detection precision, efficiency and sensitivity are improved.
It should be noted that, the detection of the moving target according to the real-time video stream, and the acquisition of the moving track of the pedestrian in the video surveillance is common knowledge and technology in the field, and can be realized by adopting the Yolo and Deep-sort algorithms.
Optionally, the step of S2, including,
s21, calculating the speed v of each pedestrian according to the motion trail of each pedestrian in the crowdj;
S22, according to the speed v of each pedestrianjDetermining the overall average velocityWherein N represents the number of pedestrians in the population;
In the above embodiment, under the condition of the panic and the quartered crowd, the overall average speed of the crowd changes more rapidly, and the corresponding speed factor of the crowd also becomes larger and is positively correlated with the panic and the quartered crowd degree.
Optionally, the trajectory of each pedestrian includes a sequence of positions of each pedestrian, the S21, including,
calculating the speed of each pedestrian according to the position sequence of each pedestrianWherein QjAnd representing the position of the jth pedestrian, and obtaining the position sequence of each pedestrian.
In the above embodiment, the speed of the pedestrian can be obtained by obtaining the ratio of the distance between the positions of the pedestrians adjacent to the preset frame number.
in the above embodiment, the change condition of the overall average speed of adjacent preset frame numbers is obtained and used as the crowd speed factor, and under the condition of crowd panic and disperse, the change of the overall average speed of the crowd is more rapid, and the corresponding crowd speed factor is increased, so that the change condition of the crowd panic and disperse is judged.
Optionally, the step of S3, including,
s31, determining the vector direction of each pedestrian according to the motion track of each pedestrian in the crowd, wherein the vector direction corresponds to 8 areas which are continuously spaced by 45 degrees in a 360-degree circumference range;
s32, according to the vector direction of each pedestrian, counting the pedestrian number ratio P in each vector directionj;
S33, according toThe number of pedestrians in each vector direction is in proportion PjCalculating the entropy W of the vector direction information of the crowdt,
According to the embodiment of the invention, the vector direction of the pedestrian can be obtained by comparing the positions of the pedestrian at preset time intervals. As shown in fig. 2, any one of the vector directions is within 8 regions at intervals of 45 degrees as shown in fig. 2.
The number of pedestrians in each vector direction is proportional to PjThe pedestrian number in the j-th area in the 8 delimited areas is proportional to the whole pedestrian number.
In the above embodiment, the vector direction information entropy characterizes the degree of misordering of the vector direction. In the case of the panic disorder of the crowd, the value of the panic disorder of the crowd is positively correlated with the panic disorder degree of the crowd.
Further, the step of S5, including,
Lt=αWt+(1-α)Vtwherein α denotes an adjustment parameter for adjusting the crowd speed factor VtAnd the evaluation index L of the entropy of the crowd vector direction information on the crowd chaos degreetThe fraction of the impact.
In the embodiment, the adjustment parameters are introduced, and the speed factor and the information entropy are associated with the crowd chaos degree evaluation index, so that the crowd panic four-scattered condition is detected, and the crowd average speed change condition and the pedestrian direction chaos degree are comprehensively considered. And moreover, by setting different adjusting parameters, the influence degree of the speed factor and the information entropy on the crowd chaos degree evaluation index can be adjusted, so that the situation of detecting the crowd panic and the four disperse situations is more flexible and convenient to adapt to different scenes.
Optionally, the tuning parameter α is 0.5.
In the above embodiment, the adjustment parameter is set to be 0.5, so that the speed factor and the information entropy have the same influence on the evaluation index of the confusion degree of the crowd, and the method is suitable for most detection situations.
The embodiment of the invention also provides a crowd panic scatter detection system, which comprises:
the motion track acquisition module is used for acquiring a real-time video stream of a monitoring scene, and detecting a motion target of the real-time video stream to obtain a motion track of each pedestrian in a crowd;
the speed factor calculation module is used for calculating a crowd speed factor V according to the motion trail of each pedestrian in the crowdtSaid representative current moment, corresponding to a current frame of said real-time video stream;
the information entropy calculating module is used for calculating the crowd vector direction information entropy W according to the motion trail of each pedestrian in the crowdt;
A chaos degree evaluation index calculation module for calculating the crowd speed factor VtAnd the entropy W of the direction information of the crowd vectortCalculating the crowd chaos degree evaluation index Lt;
An abnormality early warning module for evaluating an index L of the degree of confusion of the populationtAnd when the alarm is larger than a preset threshold S, early warning of the panic and the four-dispersing abnormity of the crowd is carried out.
The embodiment of the invention also provides a readable storage medium which comprises instructions, and when the instructions are run on electronic equipment, the electronic equipment is enabled to execute the crowd panic scatter detection method in the technical embodiment.
The embodiment of the invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can be run on the processor, wherein the processor executes the program to realize the people panic scatter detection method in the technical embodiment.
In the embodiment, the real-time video stream is acquired, the moving target is detected to acquire the pedestrian moving track, the crowd speed factor and the vector direction information entropy are acquired according to the pedestrian moving track, the crowd chaos degree evaluation index is further acquired, meanwhile, the crowd panic four-scattered abnormity early warning is automatically performed by utilizing the characteristic that the crowd chaos degree evaluation index is increased when the crowd panic four-scattered, the cost of manually monitoring the crowd panic four-scattered is saved, and the detection precision, efficiency and sensitivity are improved.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A crowd panic scatter detection method is characterized by comprising the following steps:
s1, acquiring a real-time video stream of a monitoring scene, and carrying out moving target detection on the real-time video stream to obtain a moving track of each pedestrian in a crowd;
s2, calculating a crowd speed factor V according to the motion trail of each pedestrian in the crowdt;
S3, obtaining the crowd vector direction information entropy W according to the motion trail of each pedestrian in the crowdt;
S4, according to the crowd speed factor VtAnd the entropy W of the direction information of the crowd vectortCalculating the crowd chaos degree evaluation index Lt;
S5, evaluating index L when the crowd confusion degreetAnd when the alarm is larger than a preset threshold S, early warning of the panic and the four-dispersing abnormity of the crowd is carried out.
2. The method for detecting panic disorder in people as claimed in claim 1, wherein said S2 comprises,
s21, calculating the speed v of each pedestrian according to the motion trail of each pedestrian in the crowdj;
S22, according to the speed v of each pedestrianjDetermining the overall average velocityWherein N represents the number of pedestrians in the population;
3. The method for detecting crowd panic scatter according to claim 2, wherein said each pedestrian trajectory comprises a sequence of positions of each pedestrian, said S21, comprising,
5. the method for detecting panic disorder in people as claimed in claim 1, wherein said S3 comprises,
s31, determining the vector direction of each pedestrian according to the motion track of each pedestrian in the crowd, wherein the vector direction corresponds to 8 areas which are continuously spaced by 45 degrees in a 360-degree circumference range;
s32, according to the vector direction of each pedestrian, counting the pedestrian number ratio P in each vector directionj;
S33, according to the pedestrian number ratio P in each vector directionjCalculating the entropy W of the vector direction information of the crowdt,
6. The method for detecting panic disorder in people as claimed in claim 1, wherein said S4 comprises,
Lt=αWt+(1-α)Vtwherein α denotes an adjustment parameter for adjusting the crowd speed factor VtAnd the evaluation index L of the entropy of the crowd vector direction information on the crowd chaos degreetThe fraction of the impact.
7. The method as claimed in claim 6, wherein the adjustment parameter α is 0.5.
8. A crowd panic scatter detection system, comprising:
the motion track acquisition module is used for acquiring a real-time video stream of a monitoring scene, and detecting a motion target of the real-time video stream to obtain a motion track of each pedestrian in a crowd;
the speed factor calculation module is used for calculating a crowd speed factor V according to the motion trail of each pedestrian in the crowdtSaid representative current moment, corresponding to a current frame of said real-time video stream;
the information entropy calculating module is used for calculating the crowd vector direction information entropy W according to the motion trail of each pedestrian in the crowdt;
A chaos degree evaluation index calculation module for calculating the crowd speed factor VtAnd the entropy W of the direction information of the crowd vectortCalculating the crowd chaos degree evaluation index Lt;
An abnormality early warning module for evaluating an index L of the degree of confusion of the populationtAnd when the alarm is larger than a preset threshold S, early warning of the panic and the four-dispersing abnormity of the crowd is carried out.
9. A readable storage medium comprising instructions that, when executed on an electronic device, cause the electronic device to perform the method of crowd panic scatter detection according to any one of claims 1-7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the method of detection of panic in people as claimed in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911036880.7A CN110827316A (en) | 2019-10-29 | 2019-10-29 | Crowd panic scatter detection method and system, readable storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911036880.7A CN110827316A (en) | 2019-10-29 | 2019-10-29 | Crowd panic scatter detection method and system, readable storage medium and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110827316A true CN110827316A (en) | 2020-02-21 |
Family
ID=69550937
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911036880.7A Pending CN110827316A (en) | 2019-10-29 | 2019-10-29 | Crowd panic scatter detection method and system, readable storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110827316A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112613365A (en) * | 2020-12-11 | 2021-04-06 | 北京影谱科技股份有限公司 | Pedestrian detection and behavior analysis method and device and computing equipment |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0666696A2 (en) * | 1994-02-04 | 1995-08-09 | Canon Kabushiki Kaisha | Data processing method and data processor |
JP2002197445A (en) * | 2000-12-26 | 2002-07-12 | Railway Technical Res Inst | Detector for abnormality in front of train utilizing optical flow |
US20110116682A1 (en) * | 2009-11-19 | 2011-05-19 | Industrial Technology Research Institute | Object detection method and system |
US20110175801A1 (en) * | 2010-01-15 | 2011-07-21 | Microsoft Corporation | Directed Performance In Motion Capture System |
WO2012111138A1 (en) * | 2011-02-18 | 2012-08-23 | 株式会社日立製作所 | Pedestrian movement information detection device |
CN104933412A (en) * | 2015-06-16 | 2015-09-23 | 电子科技大学 | Abnormal state detection method of medium and high density crowd |
JP2015179514A (en) * | 2014-03-19 | 2015-10-08 | 株式会社リコー | Method and apparatus for predicting motion parameters of target object |
CN105100700A (en) * | 2014-05-20 | 2015-11-25 | 三星Sds株式会社 | Target tracking device using handover between cameras and method thereof |
US20160133025A1 (en) * | 2014-11-12 | 2016-05-12 | Ricoh Company, Ltd. | Method for detecting crowd density, and method and apparatus for detecting interest degree of crowd in target position |
US20160239982A1 (en) * | 2014-08-22 | 2016-08-18 | Zhejiang Shenghui Lighting Co., Ltd | High-speed automatic multi-object tracking method and system with kernelized correlation filters |
US20160328859A1 (en) * | 2013-12-20 | 2016-11-10 | Jiangsu University | Method for detecting movement speed uniformity of scanned target in line scanning imaging process |
CN106250677A (en) * | 2016-07-21 | 2016-12-21 | 同济大学 | Under hazardous condition based on kinesiology bead model, crowd panic propagates modeling method |
US9600896B1 (en) * | 2015-11-04 | 2017-03-21 | Mitsubishi Electric Research Laboratories, Inc. | Method and system for segmenting pedestrian flows in videos |
CN106548142A (en) * | 2016-11-01 | 2017-03-29 | 浙江大学 | Crowd's incident detection and appraisal procedure in a kind of video based on comentropy |
WO2017159060A1 (en) * | 2016-03-18 | 2017-09-21 | 日本電気株式会社 | Information processing device, control method, and program |
CN107657345A (en) * | 2017-09-28 | 2018-02-02 | 北京交通大学 | A kind of pedestrian's walking behavior prediction method based on Markovian state's saltus step |
CN109086673A (en) * | 2018-07-05 | 2018-12-25 | 燕山大学 | A kind of crowd's safe coefficient appraisal procedure based on crowd density and pedestrian's speed |
CN109408889A (en) * | 2018-09-21 | 2019-03-01 | 同济大学 | Macroscopical crowd panic measure and its application based on comentropy |
US20190154872A1 (en) * | 2017-11-21 | 2019-05-23 | Reliance Core Consulting LLC | Methods, systems, apparatuses and devices for facilitating motion analysis in a field of interest |
-
2019
- 2019-10-29 CN CN201911036880.7A patent/CN110827316A/en active Pending
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0666696A2 (en) * | 1994-02-04 | 1995-08-09 | Canon Kabushiki Kaisha | Data processing method and data processor |
JP2002197445A (en) * | 2000-12-26 | 2002-07-12 | Railway Technical Res Inst | Detector for abnormality in front of train utilizing optical flow |
US20110116682A1 (en) * | 2009-11-19 | 2011-05-19 | Industrial Technology Research Institute | Object detection method and system |
US20110175801A1 (en) * | 2010-01-15 | 2011-07-21 | Microsoft Corporation | Directed Performance In Motion Capture System |
WO2012111138A1 (en) * | 2011-02-18 | 2012-08-23 | 株式会社日立製作所 | Pedestrian movement information detection device |
US20160328859A1 (en) * | 2013-12-20 | 2016-11-10 | Jiangsu University | Method for detecting movement speed uniformity of scanned target in line scanning imaging process |
JP2015179514A (en) * | 2014-03-19 | 2015-10-08 | 株式会社リコー | Method and apparatus for predicting motion parameters of target object |
CN105100700A (en) * | 2014-05-20 | 2015-11-25 | 三星Sds株式会社 | Target tracking device using handover between cameras and method thereof |
US20160239982A1 (en) * | 2014-08-22 | 2016-08-18 | Zhejiang Shenghui Lighting Co., Ltd | High-speed automatic multi-object tracking method and system with kernelized correlation filters |
US20160133025A1 (en) * | 2014-11-12 | 2016-05-12 | Ricoh Company, Ltd. | Method for detecting crowd density, and method and apparatus for detecting interest degree of crowd in target position |
CN104933412A (en) * | 2015-06-16 | 2015-09-23 | 电子科技大学 | Abnormal state detection method of medium and high density crowd |
US9600896B1 (en) * | 2015-11-04 | 2017-03-21 | Mitsubishi Electric Research Laboratories, Inc. | Method and system for segmenting pedestrian flows in videos |
WO2017159060A1 (en) * | 2016-03-18 | 2017-09-21 | 日本電気株式会社 | Information processing device, control method, and program |
CN106250677A (en) * | 2016-07-21 | 2016-12-21 | 同济大学 | Under hazardous condition based on kinesiology bead model, crowd panic propagates modeling method |
CN106548142A (en) * | 2016-11-01 | 2017-03-29 | 浙江大学 | Crowd's incident detection and appraisal procedure in a kind of video based on comentropy |
CN107657345A (en) * | 2017-09-28 | 2018-02-02 | 北京交通大学 | A kind of pedestrian's walking behavior prediction method based on Markovian state's saltus step |
US20190154872A1 (en) * | 2017-11-21 | 2019-05-23 | Reliance Core Consulting LLC | Methods, systems, apparatuses and devices for facilitating motion analysis in a field of interest |
CN109086673A (en) * | 2018-07-05 | 2018-12-25 | 燕山大学 | A kind of crowd's safe coefficient appraisal procedure based on crowd density and pedestrian's speed |
CN109408889A (en) * | 2018-09-21 | 2019-03-01 | 同济大学 | Macroscopical crowd panic measure and its application based on comentropy |
Non-Patent Citations (2)
Title |
---|
王文智等: "基于计算机视觉运动目标检测综述", 《贵州师范学院学报》 * |
陈曦等: "基于计算实验的公众恐慌研究初探", 《华中科技大学学报》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112613365A (en) * | 2020-12-11 | 2021-04-06 | 北京影谱科技股份有限公司 | Pedestrian detection and behavior analysis method and device and computing equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108053427B (en) | Improved multi-target tracking method, system and device based on KCF and Kalman | |
US20220327839A1 (en) | Movement state estimation device, movement state estimation method and program recording medium | |
Alpatov et al. | Vehicle detection and counting system for real-time traffic surveillance | |
KR101095528B1 (en) | An outomatic sensing system for traffic accident and method thereof | |
JP6532106B2 (en) | Monitoring device, monitoring method and program for monitoring | |
Huang et al. | Automatic moving object extraction through a real-world variable-bandwidth network for traffic monitoring systems | |
CN101258512A (en) | Method and image evaluation unit for scene analysis | |
KR102282800B1 (en) | Method for trackig multi target employing ridar and camera | |
KR101040049B1 (en) | Fast and robust method for tracking the multiple moving objects in video-based surveillance system | |
JP5047382B2 (en) | System and method for classifying moving objects during video surveillance | |
Ketcham et al. | The intruder detection system for rapid transit using CCTV surveillance based on histogram shapes | |
CN113484858A (en) | Intrusion detection method and system | |
Akhawaji et al. | Illegal parking detection using Gaussian mixture model and kalman filter | |
Benraya et al. | Comparison of background subtraction methods | |
US9165372B2 (en) | Improvements relating to event detection | |
CN110827316A (en) | Crowd panic scatter detection method and system, readable storage medium and electronic equipment | |
CN102496030B (en) | Identification method and identification device for dangerous targets in power monitoring system | |
CN117115752A (en) | Expressway video monitoring method and system | |
CN116543023A (en) | Multi-sensor target crowd intelligent tracking method based on correction deep SORT | |
Chen et al. | Crowd abnormal behaviour identification based on integral optical flow in video surveillance systems | |
KR20220154473A (en) | System of peventing external intrusion using virtulal detection line in image | |
Heo et al. | Autonomous reckless driving detection using deep learning on embedded GPUs | |
Jung et al. | Behavior tracking model in dynamic situation using the risk ratio EM | |
Canayaz et al. | Comparison of performance of different background subtraction methods for detection of heavy vehicles | |
Szwoch et al. | Detection of vehicles stopping in restricted zones in video from surveillance cameras |
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 |
Application publication date: 20200221 |