CN113076772A - Abnormal behavior identification method based on full modality - Google Patents
Abnormal behavior identification method based on full modality Download PDFInfo
- Publication number
- CN113076772A CN113076772A CN201911310597.9A CN201911310597A CN113076772A CN 113076772 A CN113076772 A CN 113076772A CN 201911310597 A CN201911310597 A CN 201911310597A CN 113076772 A CN113076772 A CN 113076772A
- Authority
- CN
- China
- Prior art keywords
- abnormal behavior
- full
- modality
- recognition method
- 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.)
- Pending
Links
- 206010000117 Abnormal behaviour Diseases 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 17
- 239000000523 sample Substances 0.000 claims description 18
- 230000014509 gene expression Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000036544 posture Effects 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 9
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/005—Language recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Social Psychology (AREA)
- Educational Administration (AREA)
- Acoustics & Sound (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of visual recognition, in particular to an abnormal behavior recognition method based on a full mode; collecting full-modal behavior samples and constructing an abnormal behavior sample library; the abnormal behavior characteristics are established through an algorithm, abnormal behavior personnel are automatically identified and the action track of the abnormal behavior personnel is tracked, and relevant personnel at each site are informed in real time to take corresponding measures, such as timely finding the abnormal behavior of the personnel: sudden running, falling down, pursuing and the like, and reminding the manager.
Description
Technical Field
The invention relates to the technical field of visual recognition, in particular to an abnormal behavior recognition method based on a full mode.
Background
The abnormal behaviors refer to irregular abnormal behaviors of the human body, such as sudden running, fighting, sick and falling, wandering, mass gathering of people and the like of the human body. The abnormal behavior identification technology is a technology for detecting and identifying abnormal behaviors of personnel from an acquired video sequence, can effectively prevent emergencies such as violent assaults, treading events and the like, can provide timely early warning information for monitoring personnel, and effectively assists relevant personnel to judge and take measures for abnormal conditions appearing in a monitoring scene in real time. At present, the field of human body key point detection generally tracks human body key points by using an optical flow method, so as to identify abnormal behaviors of a human body from video images of continuous frames.
The prior art can trigger early warning only when the human body is abnormal greatly, and people who are likely to break out violence such as ferocious ferocity, use special language and the like are not easy to discover. For example, in 2014, 20 minutes are allowed at 3, 1, and 21 nights, and a terrorist attack event occurs at the Kunming railway station, so that 29 people are in distress. The monitor and witness show that these terrorists dress uniformly and shout some unintelligible sentences before killing. If early warning can be carried out, more innocent lives can be saved.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an abnormal behavior identification method based on a full mode.
The technical scheme of the invention is as follows:
the abnormal behavior identification method based on the full mode is characterized by comprising the following steps: it comprises the following steps:
collecting full-modal behavior samples and constructing an abnormal behavior sample library;
secondly, detecting key points of the skeleton and recognizing the posture according to the sample data: identifying several key points of the human body, such as the head, shoulders, palm, sole;
thirdly, performing action recognition, such as running, falling, pursuing theft and fighting of the masses, according to the sample data;
fourthly, performing special language identification according to the sample data; such as foreign languages (dialects), dangerous languages, etc.;
fifthly, carrying out pedestrian attribute structurization according to the sample data: such as the color of the garment, the type of pants, the color of the backpack;
step six, establishing abnormal behavior characteristics through an algorithm, automatically identifying abnormal behavior personnel, tracking the action track of the abnormal behavior personnel, and informing relevant personnel of each site to take corresponding measures in real time, such as timely discovering the abnormal behavior of the personnel: sudden running, falling down, pursuing and the like, and reminding the manager.
Further, the collecting of the full modal behavior samples further includes expressions.
Further, the expression includes happiness, surprise, sadness, anger, disgust, and fear.
The invention has the beneficial effects that: abnormal behavior characteristics are constructed from language, expression and actual behaviors through full-modal behavior sample collection, so that dangerous behaviors are early warned in advance, managers can be assisted to strengthen people stream management, even terrorist attacks can be early warned, and innocent casualties are reduced.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the accompanying drawings:
as shown in fig. 1, the abnormal behavior recognition method based on the full modality is characterized in that: it comprises the following steps:
collecting full-modal behavior samples and constructing an abnormal behavior sample library;
secondly, detecting key points of the skeleton and recognizing the posture according to the sample data: identifying several key points of the human body, such as the head, shoulders, palm, sole;
thirdly, performing action recognition, such as running, falling, pursuing theft and fighting of the masses, according to the sample data;
fourthly, performing special language identification according to the sample data; such as foreign languages (dialects), dangerous languages, etc.;
fifthly, carrying out pedestrian attribute structurization according to the sample data: such as the color of the garment, the type of pants, the color of the backpack;
step six, establishing abnormal behavior characteristics through an algorithm, automatically identifying abnormal behavior personnel, tracking the action track of the abnormal behavior personnel, and informing relevant personnel of each site to take corresponding measures in real time, such as timely discovering the abnormal behavior of the personnel: sudden running, falling down, pursuing and the like, and reminding the manager.
The collecting full modal behavior samples further comprises expressions.
The expressions include happiness, surprise, sadness, anger, disgust, and fear.
Wherein the step of collecting the full modal behavior samples is to collect the full modal behavior samples through a Dahua network monitoring camera poe high definition 200 ten thousand H265 zoom monitor probe DH-IPC-HF2230 with a 5-50mm manual zoom lens; then the data is transmitted to a Huasan (H3C) Mini S26G26 port gigabit network management switch; the switch then transmits the data to a DELL (DELL) R730/R740 server host rack-mounted two-way to a strong ERP file sharing storage.
In the first step, data are preprocessed, and a data preprocessing algorithm comprises histogram equalization, median filtering and normalization.
And step two, step three and step four, the identification function is realized by using an identification algorithm, specifically, a scene library is firstly constructed, and then the scene library is identified.
And step five, a detection algorithm is applied, specifically pedestrian detection.
In the sixth step, a re-recognition algorithm is applied, specifically, feature extraction, similarity measurement and feature tracking.
And an edge algorithm is also applied in the fifth step and the sixth step.
The foregoing embodiments and description have been presented only to illustrate the principles and preferred embodiments of the invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention as hereinafter claimed.
Claims (9)
1. The abnormal behavior identification method based on the full mode is characterized by comprising the following steps: it comprises the following steps:
collecting full-modal behavior samples and constructing an abnormal behavior sample library;
secondly, detecting skeleton key points and recognizing postures according to the sample data;
step three, performing action recognition according to the sample data;
fourthly, performing special language identification according to the sample data;
fifthly, carrying out pedestrian attribute structurization according to the sample data;
and step six, establishing abnormal behavior characteristics through an algorithm, automatically identifying abnormal behavior personnel, tracking the action track of the abnormal behavior personnel, and informing relevant personnel of each site to take corresponding countermeasures in real time.
2. The full-modality-based abnormal behavior recognition method according to claim 1, characterized in that: the collecting full modal behavior samples further comprises expressions.
3. The full-modality-based abnormal behavior recognition method according to claim 2, characterized in that: the expressions include happiness, surprise, sadness, anger, disgust, and fear.
4. The full-modality-based abnormal behavior recognition method according to claim 3, wherein: the step of collecting the full modal behavior samples is to collect the full modal behavior samples through a Dahua network monitoring camera poe high-definition 200 ten thousand H265 zoom monitor probe DH-IPC-HF2230 containing a 5-50mm manual zoom lens; then the data is transmitted to a Huasan (H3C) Mini S26G26 port gigabit network management switch; the switch then transmits the data to a DELL (DELL) R730/R740 server host rack-mounted two-way to a strong ERP file sharing storage.
5. The full-modality-based abnormal behavior recognition method according to claim 4, wherein: in the first step, data are preprocessed, and a data preprocessing algorithm comprises histogram equalization, median filtering and normalization.
6. The full-modality-based abnormal behavior recognition method according to claim 5, wherein: and step two, step three and step four, the identification function is realized by using an identification algorithm, specifically, a scene library is firstly constructed, and then the scene library is identified.
7. The full-modality-based abnormal behavior recognition method according to claim 6, wherein: and step five, a detection algorithm is applied, specifically pedestrian detection.
8. The full-modality-based abnormal behavior recognition method according to claim 7, wherein: in the sixth step, a re-recognition algorithm is applied, specifically, feature extraction, similarity measurement and feature tracking.
9. The full-modality-based abnormal behavior recognition method according to claim 8, wherein: and an edge algorithm is also applied in the fifth step and the sixth step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911310597.9A CN113076772A (en) | 2019-12-18 | 2019-12-18 | Abnormal behavior identification method based on full modality |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911310597.9A CN113076772A (en) | 2019-12-18 | 2019-12-18 | Abnormal behavior identification method based on full modality |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113076772A true CN113076772A (en) | 2021-07-06 |
Family
ID=76608254
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911310597.9A Pending CN113076772A (en) | 2019-12-18 | 2019-12-18 | Abnormal behavior identification method based on full modality |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113076772A (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101753992A (en) * | 2008-12-17 | 2010-06-23 | 深圳市先进智能技术研究所 | Multi-mode intelligent monitoring system and method |
CN102098492A (en) * | 2009-12-11 | 2011-06-15 | 上海弘视通信技术有限公司 | Audio and video conjoint analysis-based fighting detection system and detection method thereof |
CN102348101A (en) * | 2010-07-30 | 2012-02-08 | 深圳市先进智能技术研究所 | Examination room intelligence monitoring system and method thereof |
CN103839373A (en) * | 2013-03-11 | 2014-06-04 | 成都百威讯科技有限责任公司 | Sudden abnormal event intelligent identification alarm device and system |
US20140313330A1 (en) * | 2013-04-19 | 2014-10-23 | James Carey | Video identification and analytical recognition system |
WO2018218286A1 (en) * | 2017-05-29 | 2018-12-06 | Saltor Pty Ltd | Method and system for abnormality detection |
CN109447048A (en) * | 2018-12-25 | 2019-03-08 | 苏州闪驰数控系统集成有限公司 | A kind of artificial intelligence early warning system |
CN109522793A (en) * | 2018-10-10 | 2019-03-26 | 华南理工大学 | More people's unusual checkings and recognition methods based on machine vision |
CN109615019A (en) * | 2018-12-25 | 2019-04-12 | 吉林大学 | Anomaly detection method based on space-time autocoder |
CN109635995A (en) * | 2018-10-25 | 2019-04-16 | 中国电子科技集团公司电子科学研究院 | A kind of social security events anomaly method and device based on multidimensional data |
CN110139598A (en) * | 2016-12-29 | 2019-08-16 | 关健强 | Monitoring and tracking system, method, article and equipment |
CN110176117A (en) * | 2019-06-17 | 2019-08-27 | 广东翔翼科技信息有限公司 | A kind of monitoring device and monitoring method of Behavior-based control identification technology |
-
2019
- 2019-12-18 CN CN201911310597.9A patent/CN113076772A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101753992A (en) * | 2008-12-17 | 2010-06-23 | 深圳市先进智能技术研究所 | Multi-mode intelligent monitoring system and method |
CN102098492A (en) * | 2009-12-11 | 2011-06-15 | 上海弘视通信技术有限公司 | Audio and video conjoint analysis-based fighting detection system and detection method thereof |
CN102348101A (en) * | 2010-07-30 | 2012-02-08 | 深圳市先进智能技术研究所 | Examination room intelligence monitoring system and method thereof |
CN103839373A (en) * | 2013-03-11 | 2014-06-04 | 成都百威讯科技有限责任公司 | Sudden abnormal event intelligent identification alarm device and system |
US20140313330A1 (en) * | 2013-04-19 | 2014-10-23 | James Carey | Video identification and analytical recognition system |
CN110139598A (en) * | 2016-12-29 | 2019-08-16 | 关健强 | Monitoring and tracking system, method, article and equipment |
WO2018218286A1 (en) * | 2017-05-29 | 2018-12-06 | Saltor Pty Ltd | Method and system for abnormality detection |
CN109522793A (en) * | 2018-10-10 | 2019-03-26 | 华南理工大学 | More people's unusual checkings and recognition methods based on machine vision |
CN109635995A (en) * | 2018-10-25 | 2019-04-16 | 中国电子科技集团公司电子科学研究院 | A kind of social security events anomaly method and device based on multidimensional data |
CN109447048A (en) * | 2018-12-25 | 2019-03-08 | 苏州闪驰数控系统集成有限公司 | A kind of artificial intelligence early warning system |
CN109615019A (en) * | 2018-12-25 | 2019-04-12 | 吉林大学 | Anomaly detection method based on space-time autocoder |
CN110176117A (en) * | 2019-06-17 | 2019-08-27 | 广东翔翼科技信息有限公司 | A kind of monitoring device and monitoring method of Behavior-based control identification technology |
Non-Patent Citations (4)
Title |
---|
EMONET 等: "Multi-camera open space human activity discovery for anomaly detection", 《2011 8TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS)》, 31 December 2011 (2011-12-31), pages 218 - 223 * |
杨振青: "监控视频中的异常目标检测技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 2019, 15 July 2019 (2019-07-15), pages 138 - 1177 * |
逯鹏 等: "基于稀疏超完备的异常行为检测算法", 《郑州大学学报(工学版)》, no. 06, 30 November 2016 (2016-11-30), pages 72 - 76 * |
魏永超 等: "人群异常识别技术研究进展", 《计算机系统应用》, no. 09, 15 September 2016 (2016-09-15), pages 10 - 16 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110569720B (en) | Audio and video intelligent identification processing method based on audio and video processing system | |
CN103246869B (en) | Method is monitored in crime based on recognition of face and behavior speech recognition | |
EP3279700B1 (en) | Security inspection centralized management system | |
CN111263114B (en) | Abnormal event alarm method and device | |
CN105915847A (en) | Characteristics matching and tracking based video monitoring apparatus and method | |
CN106355154B (en) | Method for detecting frequent passing of people in surveillance video | |
CN108664608A (en) | Recognition methods, device and the computer readable storage medium of a suspect | |
WO2016169282A1 (en) | Security inspection image discrimination system and image discrimination method comprising video analysis | |
CN109376639A (en) | Adjoint personnel's early warning system and method based on Identification of Images | |
CN113223046B (en) | Method and system for identifying prisoner behaviors | |
CN112565676A (en) | Method, system and equipment for identifying violation of on-duty personnel based on intelligent camera | |
CN109961587A (en) | A kind of monitoring system of self-service bank | |
KR20200052418A (en) | Automated Violence Detecting System based on Deep Learning | |
CN109389794A (en) | A kind of Intellectualized Video Monitoring method and system | |
CN110490126B (en) | Safe deposit box safety control system based on artificial intelligence | |
CN111862413A (en) | Method and system for realizing epidemic situation resistant non-contact multidimensional identity rapid identification | |
US20210364356A1 (en) | System and method for using artificial intelligence to enable elevated temperature detection of persons using commodity-based thermal cameras | |
CN113850229A (en) | Method and system for early warning abnormal behaviors of people based on video data machine learning and computer equipment | |
CN113269127A (en) | Face recognition and pedestrian re-recognition monitoring method and system for real-time automatic database building | |
CN116416281A (en) | Grain depot AI video supervision and analysis method and system | |
CN105354552A (en) | Human face identification and expression analysis based online monitoring system and method | |
CN204926116U (en) | Picture system is declared in safety inspection containing video analysis | |
CN108171187A (en) | A kind of abnormal behaviour automatic identifying method and device based on the extraction of bone point | |
Lamba et al. | Information Retrieval from Emotions and Eye Blinks with help of Sensor Nodes. | |
CN109858400A (en) | Database matching system is captured in recognition of face |
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 |