CN112364680A - Abnormal behavior detection method based on optical flow algorithm - Google Patents
Abnormal behavior detection method based on optical flow algorithm Download PDFInfo
- Publication number
- CN112364680A CN112364680A CN202010985851.1A CN202010985851A CN112364680A CN 112364680 A CN112364680 A CN 112364680A CN 202010985851 A CN202010985851 A CN 202010985851A CN 112364680 A CN112364680 A CN 112364680A
- Authority
- CN
- China
- Prior art keywords
- optical flow
- amplitude
- entropy
- histogram
- flow algorithm
- 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.)
- Granted
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 92
- 206010000117 Abnormal behaviour Diseases 0.000 title claims abstract description 50
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 230000006399 behavior Effects 0.000 claims abstract description 25
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 8
- 230000000739 chaotic effect Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 4
- 208000012661 Dyskinesia Diseases 0.000 description 2
- AYFVYJQAPQTCCC-GBXIJSLDSA-N L-threonine Chemical compound C[C@@H](O)[C@H](N)C(O)=O AYFVYJQAPQTCCC-GBXIJSLDSA-N 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an abnormal behavior detection method based on an optical flow algorithm, which is implemented according to the following steps: step 1, extracting optical flow information by an optical flow algorithm: extracting optical flow information generated during human body movement by adopting a Farneback dense optical flow algorithm; step 2, extracting behavior characteristics: counting the optical flow information extracted in the step 1 into a direction amplitude histogram; step 3, result analysis and abnormity judgment: whether abnormal behaviors occur is judged by calculating the direction and amplitude entropy of the histogram, the larger the direction and amplitude entropy of the histogram is, the more disordered the current motion is, the higher the possibility of representing the abnormal behaviors is, and the problem that misjudgment of the abnormal behaviors is easy to occur in the prior art is solved.
Description
Technical Field
The invention belongs to the technical field of intelligent video monitoring, and relates to an abnormal behavior detection method based on an optical flow algorithm.
Background
At present, the abnormal behaviors are defined in public places such as parking lots and railway stations as follows: different from the normal walking behavior of human body, the fighting and robbery behavior with the characteristics of high movement speed and disordered movement direction is defined as abnormal behavior.
In recent years, in many public places, rapid behaviors with illegal criminal properties, such as putting up, robbery and the like, frequently occur, such as parking lots, railway stations, shopping malls and the like, the behaviors seriously disturb the public order of society, and simultaneously bring much personal injury and property loss to people. Video surveillance research is also gaining increasing attention in order to minimize the risk. Countless cameras are installed in parking lots, railway stations and various public places of shopping malls, and guarantee is brought to social safety. If in some public places with dense population, the intelligent monitoring system can give an alarm in time when detecting abnormal conditions, and the life and property safety of the masses can be effectively ensured.
The abnormal behaviors of the human body are generally expressed as abnormal movement speed and abnormal movement direction, and the traditional detection method is a feature extraction method and has the problems of poor detection effect, easy misjudgment of abnormal behaviors, complex calculation method and the like.
Disclosure of Invention
The invention aims to provide an abnormal behavior detection method based on an optical flow algorithm, which solves the problem that misjudgment of abnormal behaviors is easy to occur in the prior art.
The invention adopts the technical scheme that an abnormal behavior detection method based on an optical flow algorithm is implemented according to the following steps:
step 1, extracting optical flow information by an optical flow algorithm: extracting optical flow information generated during human body movement by adopting a Farneback dense optical flow algorithm;
step 2, extracting behavior characteristics: counting the optical flow information extracted in the step 1 into a direction amplitude histogram;
step 3, result analysis and abnormity judgment: whether abnormal behaviors occur is judged by calculating the direction and amplitude entropy of the histogram, and the larger the direction and amplitude entropy of the histogram is, the more chaotic the current motion is, and the higher the possibility of representing the abnormal behaviors occurs.
The invention is also characterized in that:
the step 2 is implemented according to the following steps:
step 2.1: conversion of plane rectangular coordinates to polar coordinates
The interframe optical flow field calculated by the Farneback dense optical flow algorithm is an original feature obtained from a video image, and an optical flow vector can be represented by a four-dimensional vector (x, y, u, v), wherein (x, y) represents spatial position information of the optical flow vector in the image, and (u, v) represents the magnitude of components of the optical flow vector in the horizontal direction and the vertical direction respectively;
step 2.2: matlab software is utilized to convert vector information of optical flow into histogram
The direction amplitude histogram is adopted to describe the behavior of the human body when moving, the abscissa is set into a plurality of intervals, and the size of each interval is
The ordinate represents the statistical value of the magnitude of the amplitude value in each interval.
In step 2.1, the optical flow vector components (u, v) are converted from a plane rectangular coordinate form to a (r, theta) form in a polar coordinate form, and the size of the optical flow can be obtained through calculation and analysis
Direction of light flow
In step 2.2, the abscissa is set to 12 intervals.
Step 3 is specifically implemented according to the following steps:
step 3.1: let the amplitude of the ith interval be hiThe sum of the directional times of the i interval is siBefore calculating the entropy of the direction and the amplitude, the probability of the direction and the amplitude of each interval is calculated, and the calculation formula is as follows:
Sdir: the sum of the number of times of direction of the direction amplitude histogram;
Shyp: the sum of the directional magnitude histogram magnitudes;
the direction entropy and the amplitude entropy calculation formulas are as follows:
directional entropy:
amplitude entropy:
the direction entropy and the amplitude entropy are one of important factors for judging whether abnormal behaviors exist, so that the direction entropy and the amplitude entropy can be integrated into a formula which is expressed as the following formula:
W＝ES×Eh；
the larger W, the more chaotic the current motion is, and the more likely it is that abnormal behavior occurs.
The invention has the beneficial effects that: the invention relates to an abnormal behavior detection method based on an optical flow algorithm, which solves the problems of poor detection effect, easy misjudgment of abnormal behaviors, complex calculation method and the like in the prior art; and extracting optical flow information by adopting a Farneback dense optical flow algorithm, analyzing the behavior of the human body through the optical flow information generated during the motion of the human body, and judging whether the human body belongs to abnormal behavior. The optical flow method does not need to acquire the background of the image in advance, and the calculation result only depends on the relative motion of continuous frames and is not influenced by a complex environment; the concept of entropy is introduced, wherein the entropy is used for describing the state of a substance in thermodynamics, and the physical meaning of the entropy is to represent the chaos degree of a system. When abnormal behavior occurs, the direction of each part of the body is disordered, and the like, so whether the abnormal behavior exists can be judged by adopting whether the entropy value is larger than a certain threshold value.
Drawings
FIG. 1 is a flow chart of an abnormal behavior detection method based on an optical flow algorithm according to the present invention;
FIG. 2 is a technical roadmap of the abnormal behavior detection method based on optical flow algorithm of the present invention;
FIG. 3a is a W curve of normal walking of the abnormal behavior detection method based on the optical flow algorithm of the present invention;
FIG. 3b is a curve of framing behavior W of the abnormal behavior detection method based on the optical flow algorithm;
FIG. 3c is a robbery behavior W curve of the abnormal behavior detection method based on the optical flow algorithm.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention discloses an abnormal behavior detection method based on an optical flow algorithm, which is implemented by the following steps as shown in figure 1:
step 1, extracting optical flow information by an optical flow algorithm: extracting optical flow information generated during human body movement by adopting a Farneback dense optical flow algorithm;
as shown in fig. 2, specifically, the dense optical flow is calculated in OpenCV using the API of calcptical flowfarnback (), where parameters of the function of calcptical flowfarnback are specifically set to (prvs, next, None,0.5,3,15,3,5,1.2,0), a first parameter represents an input previous frame image, a second parameter represents an input subsequent frame image, a third parameter represents an output optical flow, a fourth parameter represents a pyramid scaling parameter, a fifth parameter represents a pyramid layer number, a sixth parameter represents a window size, a seventh parameter represents an iteration number, an eighth parameter represents a pixel neighborhood size, a ninth parameter represents a gaussian standard deviation, and a tenth parameter flag represents a calculation mode.
Step 2, extracting behavior characteristics: counting the optical flow information extracted in the step 1 into a direction amplitude histogram;
the step 2 is implemented according to the following steps:
step 2.1: conversion of plane rectangular coordinates to polar coordinates
The interframe optical flow field calculated by the Farneback dense optical flow algorithm is an original feature obtained from a video image, and an optical flow vector can be represented by a four-dimensional vector (x, y, u, v), wherein (x, y) represents spatial position information of the optical flow vector in the image, and (u, v) represents the magnitude of components of the optical flow vector in the horizontal direction and the vertical direction respectively; in step 2.1, the optical flow vector components (u,v) converting the plane rectangular coordinate form into a (r, theta) form under a polar coordinate, and obtaining the magnitude of the optical flow through calculation and analysis
Direction of light flow
Step 2.2: matlab software is utilized to convert vector information of optical flow into histogram
The traditional direction histogram is a nonparametric estimation method, although the traditional direction histogram can represent the optical flow characteristics of a moving object, the change of amplitude values in the direction in optical flow information is ignored, so that the direction amplitude histogram is adopted to describe the behavior of the human body in motion, the abscissa is set into a plurality of regions, and the size of each region is equal to
The ordinate represents the statistical value of the magnitude of the amplitude value in each interval. In step 2.2, the abscissa is set to 12 intervals.
Step 3, result analysis and abnormity judgment: whether abnormal behaviors occur is judged by calculating the direction and amplitude entropy of the histogram, and the larger the direction and amplitude entropy of the histogram is, the more chaotic the current motion is, and the higher the possibility of representing the abnormal behaviors occurs.
Step 3 is specifically implemented according to the following steps:
step 3.1: let the amplitude of the ith interval be hiThe sum of the directional times of the i interval is siBefore calculating the entropy of the direction and the amplitude, the probability of the direction and the amplitude of each interval is calculated, and the calculation formula is as follows:
Sdir: the sum of the number of times of direction of the direction amplitude histogram;
Shyp: the sum of the directional magnitude histogram magnitudes;
the direction entropy and the amplitude entropy calculation formulas are as follows:
directional entropy:
amplitude entropy:
the direction entropy and the amplitude entropy are one of important factors for judging whether abnormal behaviors exist, so that the direction entropy and the amplitude entropy can be integrated into a formula which is expressed as the following formula:
W＝ES×Eh；
the larger W, the more chaotic the current motion is, and the more likely it is that abnormal behavior occurs.
The invention relates to an abnormal behavior detection method based on an optical flow algorithm, which comprises the following steps: the function of step 1 is to extract optical flow features in the video sequence images.
Adopting Farneback dense optical flow algorithm to extract optical flow characteristics, the principle is as follows: firstly, the brightness between adjacent frames is assumed to be constant, the frame taking time of the adjacent video frames is continuous, or the motion of an object between the adjacent frames is small, and meanwhile, the space consistency is kept, namely, pixel points of the same sub-image have the same motion. The main idea of Farneback dense optical flow is to approximate neighborhood information for each pixel using a polynomial, e.g., consider a quadratic polynomial f (x) xTAx+bTx + c, a is a symmetric matrix, b is a vector, c is a scalar, f (x) is expressed as an approximate description of the neighborhood information of the pixel, a is obtained by least-squares weighted fitting of the neighborhood information of the pixel, and the weight coefficients are related to the size and position of the pixels of the neighborhood. If the image of the previous frame is used
Representing the displacement of two frame images by d, then
Because the appearance information of the pixels in the image scene is not changed when the frames move, the same corresponding coefficient can be obtained, and if the corresponding coefficient is a non-singular matrix, the displacement is realized
And tracking the characteristic points of the image by combining the optimization and adjustment of the error with the image pyramid.
The Farneback dense optical flow algorithm is adopted to extract the optical flow characteristics, and the method has the advantages that: the dense optical flow algorithm can calculate the offset of all points on the image to form a dense optical flow field, and the pixel-level image registration can be performed by using the dense optical flow field, so that the effect after registration is obviously superior to that of sparse optical flow registration.
Examples
1) In this example, a CASIA action data set is used, which has 1446 video data in total and is shot by cameras distributed at three different viewing angles in an outdoor parking lot environment. The data is divided into single-person behaviors and multi-person interactive behaviors, and the single-person behaviors comprise the following eight different behaviors: "walk", "run", "stoop", "jump", "crouch", "dizzy", "loitering" and "pound the car", 24 people are involved in each action, about 4 times per person. The multi-person interactive behaviors include seven different behaviors: robbery, shelving, tailing, chasing, head collision, convergence and overrunning, once or twice for every two persons. The background in the video is complex, the light change is obvious, the frame rate is 25fps, the resolution is 320 multiplied by 240, huffyuv coding compression is adopted, and the video is stored in the form of an avi file.
In the experiment, the fighting and robbery behaviors with characteristics of high movement speed and inconsistent movement directions, which are different from the normal behaviors (walking) of the human body, are defined as abnormal behaviors.
2) The experimental training uses a Windows 10 system, a processor inter (R) core (TM) i5-8250U CPU @1.60GHz 1.80GHz and 8.00GB memory, and the integrated development environment is Pycharm, OpenCV open source library and Matlab R2016 a.
3) In order to extract optical flow information in a motion area more accurately, an effective optical flow is introduced on the basis of the traditional optical flow, namely, only optical flow points which have larger contribution to abnormal behavior detection are reserved and the rest optical flow points are omitted through screening of the amplitude of the optical flow.
The effective optical flow field can be obtained by the following formula:
wherein thre: the threshold value of the screening light flow point is selected after a plurality of experiments, and the thre is 0.3.
4) When a fighting or robbery action occurs, the movement direction is disordered and the W value increases, so that the change of the optical flow characteristics is reflected well by the W value, and the W change curves of different actions are shown in fig. 3(a) to (c).
(a) And (c) W change curves of normal walking, fighting and robbery in a scene are respectively shown, the W mean value of the normal walking is smaller, and the W mean value of the fighting and robbery is larger in comparison with the W mean values of the three different behaviors, so that the W value has better discrimination between the normal behavior and the abnormal behavior, and the larger the W value is, the higher the possibility of the abnormal behavior is.
The invention relates to an abnormal behavior detection method based on an optical flow algorithm, which solves the problems of poor detection effect, easy misjudgment of abnormal behaviors, complex calculation method and the like in the prior art; and extracting optical flow information by adopting a Farneback dense optical flow algorithm, analyzing the behavior of the human body through the optical flow information generated during the motion of the human body, and judging whether the human body belongs to abnormal behavior. The optical flow method does not need to acquire the background of the image in advance, and the calculation result only depends on the relative motion of continuous frames and is not influenced by a complex environment; the concept of entropy is introduced, wherein the entropy is used for describing the state of a substance in thermodynamics, and the physical meaning of the entropy is to represent the chaos degree of a system. When abnormal behavior occurs, the direction of each part of the body is disordered, and the like, so whether the abnormal behavior exists can be judged by adopting whether the entropy value is larger than a certain threshold value.
Claims (5)
1. An abnormal behavior detection method based on an optical flow algorithm is characterized by comprising the following steps:
step 1, extracting optical flow information by an optical flow algorithm: extracting optical flow information generated during human body movement by adopting a Farneback dense optical flow algorithm;
step 2, extracting behavior characteristics: counting the optical flow information extracted in the step 1 into a direction amplitude histogram;
step 3, result analysis and abnormity judgment: whether abnormal behaviors occur is judged by calculating the direction and amplitude entropy of the histogram, and the larger the direction and amplitude entropy of the histogram is, the more chaotic the current motion is, and the higher the possibility of representing the abnormal behaviors occurs.
2. The method for detecting abnormal behavior based on optical flow algorithm as claimed in claim 1, wherein the step 2 is implemented by the following steps:
step 2.1: conversion of plane rectangular coordinates to polar coordinates
The interframe optical flow field calculated by the Farneback dense optical flow algorithm is an original feature obtained from a video image, and an optical flow vector can be represented by a four-dimensional vector (x, y, u, v), wherein (x, y) represents spatial position information of the optical flow vector in the image, and (u, v) represents the magnitude of components of the optical flow vector in the horizontal direction and the vertical direction respectively;
step 2.2: matlab software is utilized to convert vector information of optical flow into histogram
The direction amplitude histogram is adopted to describe the behavior of the human body when moving, the abscissa is set into a plurality of intervals, and the size of each interval is
The ordinate represents the statistical value of the magnitude of the amplitude value in each interval.
3. The method as claimed in claim 2, wherein in step 2.1, the optical flow vector components (u, v) are converted from plane rectangular coordinates to polar coordinates (r, θ), and the magnitude of the optical flow is calculated and analyzed
Direction of light flow
4. The method according to claim 2, wherein in step 2.2, the abscissa is set to 12 intervals.
5. The method for detecting abnormal behavior based on optical flow algorithm as claimed in claim 2, wherein the step 3 is implemented by the following steps:
step 3.1: let the amplitude of the ith interval be hiThe sum of the directional times of the i interval is siBefore calculating the entropy of the direction and the amplitude, the probability of the direction and the amplitude of each interval is calculated, and the calculation formula is as follows:
Sdir: the sum of the number of times of direction of the direction amplitude histogram;
Shyp: the sum of the directional magnitude histogram magnitudes;
the direction entropy and the amplitude entropy calculation formulas are as follows:
directional entropy:
amplitude entropy:
the direction entropy and the amplitude entropy are one of important factors for judging whether abnormal behaviors exist, so that the direction entropy and the amplitude entropy can be integrated into a formula which is expressed as the following formula:
W＝ES×Eh；
the larger W, the more chaotic the current motion is, and the more likely it is that abnormal behavior occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010985851.1A CN112364680B (en) | 2020-09-18 | 2020-09-18 | Abnormal behavior detection method based on optical flow algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010985851.1A CN112364680B (en) | 2020-09-18 | 2020-09-18 | Abnormal behavior detection method based on optical flow algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112364680A true CN112364680A (en) | 2021-02-12 |
| CN112364680B CN112364680B (en) | 2024-03-05 |
Family
ID=74516561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010985851.1A Active CN112364680B (en) | 2020-09-18 | 2020-09-18 | Abnormal behavior detection method based on optical flow algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112364680B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537165A (en) * | 2021-09-15 | 2021-10-22 | 湖南信达通信息技术有限公司 | Detection method and system for pedestrian alarm |
| CN113610012A (en) * | 2021-08-10 | 2021-11-05 | 腾讯音乐娱乐科技（深圳）有限公司 | Video detection method, electronic device and computer-readable storage medium |
| CN113870323A (en) * | 2021-09-30 | 2021-12-31 | 西安交通大学 | Structural surface micro-crack identification method based on optical flow information entropy |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100030059A1 (en) * | 2007-02-15 | 2010-02-04 | Tecdata Ag | Method for Measuring Information of Biological Systems |
| US20110243401A1 (en) * | 2010-03-31 | 2011-10-06 | Zabair Adeala T | System and method for image sequence processing |
| CN102629384A (en) * | 2012-02-28 | 2012-08-08 | 成都三泰电子实业股份有限公司 | Method for detecting abnormal behavior during video monitoring |
| CN102880444A (en) * | 2012-08-24 | 2013-01-16 | 浙江捷尚视觉科技有限公司 | Fighting detecting method based on stereoscopic vision motion field analysis |
| CN103810718A (en) * | 2012-11-15 | 2014-05-21 | 浙江大华技术股份有限公司 | Method and device for detection of violently moving target |
| CN104123544A (en) * | 2014-07-23 | 2014-10-29 | 通号通信信息集团有限公司 | Video analysis based abnormal behavior detection method and system |
| CN106326840A (en) * | 2016-08-11 | 2017-01-11 | 电子科技大学 | Method for detecting abnormal behaviors of group of people based on optical flow histogram entropy |
| CN106327791A (en) * | 2016-08-31 | 2017-01-11 | 朱明� | Exceptional event real-time alarm method and system |
| US20170171499A1 (en) * | 2015-12-15 | 2017-06-15 | Canon Kabushiki Kaisha | Method, system and apparatus for spatially arranging a plurality of video frames for display |
| US20170261264A1 (en) * | 2017-05-25 | 2017-09-14 | Northeastern University | Fault diagnosis device based on common information and special information of running video information for electric-arc furnace and method thereof |
| CN107967440A (en) * | 2017-09-19 | 2018-04-27 | 北京工业大学 | A kind of monitor video method for detecting abnormality based on multizone mutative scale 3D-HOF |
-
2020
- 2020-09-18 CN CN202010985851.1A patent/CN112364680B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100030059A1 (en) * | 2007-02-15 | 2010-02-04 | Tecdata Ag | Method for Measuring Information of Biological Systems |
| US20110243401A1 (en) * | 2010-03-31 | 2011-10-06 | Zabair Adeala T | System and method for image sequence processing |
| CN102629384A (en) * | 2012-02-28 | 2012-08-08 | 成都三泰电子实业股份有限公司 | Method for detecting abnormal behavior during video monitoring |
| CN102880444A (en) * | 2012-08-24 | 2013-01-16 | 浙江捷尚视觉科技有限公司 | Fighting detecting method based on stereoscopic vision motion field analysis |
| CN103810718A (en) * | 2012-11-15 | 2014-05-21 | 浙江大华技术股份有限公司 | Method and device for detection of violently moving target |
| CN104123544A (en) * | 2014-07-23 | 2014-10-29 | 通号通信信息集团有限公司 | Video analysis based abnormal behavior detection method and system |
| US20170171499A1 (en) * | 2015-12-15 | 2017-06-15 | Canon Kabushiki Kaisha | Method, system and apparatus for spatially arranging a plurality of video frames for display |
| CN106326840A (en) * | 2016-08-11 | 2017-01-11 | 电子科技大学 | Method for detecting abnormal behaviors of group of people based on optical flow histogram entropy |
| CN106327791A (en) * | 2016-08-31 | 2017-01-11 | 朱明� | Exceptional event real-time alarm method and system |
| US20170261264A1 (en) * | 2017-05-25 | 2017-09-14 | Northeastern University | Fault diagnosis device based on common information and special information of running video information for electric-arc furnace and method thereof |
| CN107967440A (en) * | 2017-09-19 | 2018-04-27 | 北京工业大学 | A kind of monitor video method for detecting abnormality based on multizone mutative scale 3D-HOF |
Non-Patent Citations (6)
| Title |
|---|
| HUIFANG QIAN 等: "Abnormal Behavior Detection and Recognition Method Based on Improved ResNet Model", 《CMC-COMPUTERS, MATERIALS & CONTINUA》, vol. 65, no. 3, 25 June 2020 (2020-06-25), pages 2153 - 2167 * |
| RENSSO VICTOR HUGO MORA COLQUE 等: "Histograms of Optical Flow Orientation and Magnitude and Entropy to Detect Anomalous Events in Videos", 《IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》, vol. 27, no. 3, 31 March 2017 (2017-03-31), pages 376 - 682 * |
| 丁茜 等: "基于监控视频的异常事件识别", 《光学仪器》, vol. 41, no. 1, pages 2 - 3 * |
| 周曼 等: "基于光流法的深度学习在工业运动检测的应用", 《自动化与仪表》, vol. 34, no. 7, pages 1 - 2 * |
| 安井然: "视频监控系统中异常行为检测软件设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》, pages 138 - 1062 * |
| 王燕妮 等: "关键帧结合幅值直方图熵的异常行为检测算法", 《计算机与数字工程》, vol. 47, no. 9, 20 September 2019 (2019-09-20), pages 2281 - 2285 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610012A (en) * | 2021-08-10 | 2021-11-05 | 腾讯音乐娱乐科技（深圳）有限公司 | Video detection method, electronic device and computer-readable storage medium |
| CN113537165A (en) * | 2021-09-15 | 2021-10-22 | 湖南信达通信息技术有限公司 | Detection method and system for pedestrian alarm |
| CN113537165B (en) * | 2021-09-15 | 2021-12-07 | 湖南信达通信息技术有限公司 | Detection method and system for pedestrian alarm |
| CN113870323A (en) * | 2021-09-30 | 2021-12-31 | 西安交通大学 | Structural surface micro-crack identification method based on optical flow information entropy |
| CN113870323B (en) * | 2021-09-30 | 2024-04-02 | 西安交通大学 | Structure surface micro crack identification method based on optical flow information entropy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112364680B (en) | 2024-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wen et al. | Detection, tracking, and counting meets drones in crowds: A benchmark | |
| CN108830252B (en) | Convolutional neural network human body action recognition method fusing global space-time characteristics | |
| WO2020173226A1 (en) | Spatial-temporal behavior detection method | |
| CN112364680B (en) | Abnormal behavior detection method based on optical flow algorithm | |
| JP5986689B2 (en) | System and method for processing visual information for event detection | |
| US9665777B2 (en) | System and method for object and event identification using multiple cameras | |
| US8073203B2 (en) | Generating effects in a webcam application | |
| CN106203513B (en) | A kind of statistical method based on pedestrian's head and shoulder multi-target detection and tracking | |
| Zhang et al. | Abnormal crowd behavior detection based on social attribute-aware force model | |
| Zhu et al. | Video anomaly detection for smart surveillance | |
| Cao et al. | Abnormal crowd motion analysis | |
| Sengar et al. | Motion detection using block based bi-directional optical flow method | |
| WO2003054801A1 (en) | Identifying moving objects in a video using volume growing and change detection masks | |
| CN112380905B (en) | Abnormal behavior detection method based on histogram combination entropy of monitoring video | |
| Hu et al. | A novel approach for crowd video monitoring of subway platforms | |
| Harville | Stereo person tracking with short and long term plan-view appearance models of shape and color | |
| WO2022095818A1 (en) | Methods and systems for crowd motion summarization via tracklet based human localization | |
| KR20200060868A (en) | multi-view monitoring system using object-oriented auto-tracking function | |
| Lin et al. | Compressed-domain fall incident detection for intelligent homecare | |
| Khashman | Automatic detection, extraction and recognition of moving objects | |
| Makantasis et al. | Student-t background modeling for persons' fall detection through visual cues | |
| Yang et al. | Human activity recognition based on the blob features | |
| Choi et al. | A view-based real-time human action recognition system as an interface for human computer interaction | |
| Wei et al. | Crowd density field estimation based on crowd dynamics theory and social force model | |
| ELBAŞI et al. | Control charts approach for scenario recognition in video sequences |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |