Abnormal behavior detection method and system

A detection method and behavioral technology, applied in the field of intelligent identification, can solve the problems of missed detection and negative, cumbersome and inconvenient, and cannot meet the needs of video surveillance

Active Publication Date: 2019-08-16
GUANGZHOU UNIVERSITY
View PDF5 Cites 55 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the monitoring system often only performs simple recording and transmission of video signals, and still stays in manual monitoring of video signals by monitoring personnel and post-event video analysis. There are shortcomings such as huge workload, slow response to abnormal events, or missed detection and reporting.
Especially for the detection of sudden abnormal events, due to the randomness of abnormal behaviors and no specific rules to be found, obviously, this method of relying on manual detection of abnormal events is far from meeting the needs of current video surveillance. A monitoring method that can directly process and identify is imminent
[0004] Commonly used dangerous person detection on the market can only manually identify knives through X-rays, or use traditional algorithms to detect knives, and then manually judge, which is very cumbersome and inconvenient

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Abnormal behavior detection method and system
  • Abnormal behavior detection method and system
  • Abnormal behavior detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0128] Such as figure 1 As shown, a single-person abnormal behavior detection method includes steps:

[0129] S1. Use the neural network human skeleton extraction model to extract the dynamic human skeleton joint points in the video to form a skeleton data set;

[0130] S2. Obtain a higher-level behavioral feature map corresponding to the skeleton through the ST-GCN (space-time graph convolution) network, that is, the surface behavioral feature;

[0131] S3. Input the behavior feature map into the abnormal behavior classifier model, and match to identify the behavior type;

[0132] S4. Use the yolov3 feature extraction model to detect dangerous goods, such as identifying and detecting knives;

[0133] 1, wherein, the establishment steps of described human skeleton extraction model are as follows:

[0134] Divide the human skeleton into five parts, namely two arms, two legs and a torso;

[0135] Use 3D conversion technology to select the physical structure of the joints and...

Embodiment 2

[0255] A multi-person abnormal behavior detection method, wherein multi-person pose estimation is based on single-person pose estimation, and the overall processing process of the model is:

[0256] ①Read a picture with width w×height h;

[0257] ②The 10-layer VGG-19 network is passed to train an image feature F that is also w×h;

[0258] ③Introduce two layers of different convolutional neural networks, you can get:

[0259] Key point confidence network S=(S 1 ,S 2 ,...,S J ) where J represents that there are J parts in the human body:

[0260] S j ∈R w×h ,j∈{1...J}.

[0261] Keypoint affinity vector field L c ∈R w×h×2 ,c∈{1,...,C}.

[0262] ④The key points are clustered to obtain the skeleton, and the schematic diagram of the key point confidence network and affinity vector field network is as follows: Figure 9 As shown, S is the confidence network, and L is the affinity vector field network:

[0263]

[0264]

[0265] The loss function of the whole model i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an abnormal behavior detection method, which comprises the following steps of: extracting dynamic human skeleton joints in a video by using a neural network human skeleton extraction model to form a skeleton data set; obtaining a higher-level behavior feature map corresponding to the bone, namely surface behavior features, by an ST-GCN network; and inputting the behavior feature map into the abnormal behavior classifier model, and performing matching to identify the behavior type. The invention also discloses an abnormal behavior detection system which comprises a videomonitoring module and a network model integration module. According to the method, various human body behaviors and a large amount of human body skeleton data can be accurately and efficiently processed, and abnormal behaviors appearing in video monitoring can be automatically identified.

Description

technical field [0001] The invention relates to the field of intelligent identification, in particular to an abnormal behavior detection method and system thereof. Background technique [0002] The era of artificial intelligence has quietly arrived. Based on this background, intelligent recognition is the theme of today's world. Face recognition, as a hot research issue in the field of pattern recognition, has received extensive attention. The intelligent recognition of abnormal behavior is in line with the current public Safety requirements are aimed at improving the level of artificial intelligence in the practical field of life, and establishing intelligent recognition algorithms with adaptability and resource efficiency. [0003] At present, the monitoring system often only simply records and transmits the video signal, and still stays in the manual monitoring of the video signal by the monitoring personnel and the post-event video analysis. There are shortcomings such a...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06N3/049G06V40/20G06F18/24
Inventor 伍冯洁潘伟旋詹逸李锦韬林佳翰郑振勤黄成浩
Owner GUANGZHOU UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap