Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Behavior detection and identification method and system

An identification method and behavior technology, applied in the field of computer identification, can solve the problems of large amount of calculation, cost and timeliness of abnormal behavior analysis methods, etc., to improve detection reliability, prevent missed detection, and achieve good complementarity. Effect

Active Publication Date: 2021-08-24
SHANDONG UNIV
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The abnormal behavior analysis method based on the deep neural network model has a large amount of calculation and needs to rely on high-performance parallel computing equipment, and the cost and timeliness need to be improved

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
  • Behavior detection and identification method and system
  • Behavior detection and identification method and system
  • Behavior detection and identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] like figure 1 As shown, Embodiment 1 of the present invention provides a behavior detection and recognition system, which includes:

[0046] Calculation module, for obtaining the binarized differential image sequence of the behavioral video stream, calculating the middle center of mass movement velocity, left centroid movement velocity and right centroid movement velocity of each frame of binarization difference image;

[0047] The judging module is used to compare the motion speed of the center of mass, the motion speed of the left center of mass and the motion speed of the right center of mass with the preset speed threshold, and if one or more of the three center of mass motion speeds is greater than the speed threshold, it is determined that Behavior is speeding, otherwise it is judged not speeding;

[0048] The behavior detection and alarm module is used to count the number of speeding times per unit time. If the number of speeding times is greater than the preset...

Embodiment 2

[0072] In Embodiment 2, a surveillance video-based detection method and system for violent limb behavior is provided, including preprocessing the video stream to obtain continuous grayscale images, obtaining binarized difference images, center centroid and left , the calculation of the right center of mass, the calculation of the movement speed of the three centers of mass, the detection and alarm of violent body behavior, and other steps, through the lightweight algorithm to obtain the body movement speed of the characters in the video, quickly detect the violent body behavior of the characters and give an alarm.

[0073] like figure 2 As shown, in the present embodiment 2, the violent body behavior detection system based on the monitoring video includes a video stream preprocessing module (the same as the preprocessing unit in the embodiment 1), a binarized difference image acquisition module (the same as that obtained in the embodiment 1) unit), three centroid calculation ...

Embodiment 3

[0096] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium includes instructions for executing a behavior detection and recognition method, the method includes:

[0097] Obtain the binary difference image sequence of the behavioral video stream, and calculate the middle centroid movement velocity, left centroid movement velocity and right centroid movement velocity of each frame of the binarization difference image;

[0098] Compare the motion speed of the middle center of mass, the left center of mass, and the right center of mass with the preset speed threshold, if one or more of the three center of mass motion speeds is greater than the speed threshold, it is determined that the behavior in the image is overspeed, Otherwise, it is judged as not speeding;

[0099] The number of speeding behaviors is counted per unit time. If the number of speeding times is greater than the prese...

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 provides a behavior detection and identification method and system, and belongs to the technical field of computer vision. The method comprises the steps: obtaining a binary difference image sequence of a behavior video stream, calculating a middle mass center movement speed, a left mass center movement speed and a right mass center movement speed of each frame of image, comparing with a preset speed threshold value; if one or more of the three mass center movement speeds are greater than a speed threshold value, judging that the behavior in the image is overspeed, otherwise, judging that the behavior is not overspeed; counting the behavior overspeed times in unit time, if the overspeed times are larger than a preset overspeed times threshold value, judging that a violent limb behavior is detected, and giving an alarm, and otherwise, clearing away the recorded overspeed times, and starting a new statistical period. According to the invention, the movement speeds of a middle mass center, a left mass center and a right mass center are calculated, the algorithm is simple, the three mass centers have good complementarity, severe limb behaviors can be detected, missing detection and false detection are prevented, the detection reliability is improved, high-performance parallel computing equipment does not need to be arranged, and the cost performance is high.

Description

technical field [0001] The invention relates to the technical field of computer identification, in particular to a monitoring video-based behavior detection and identification method and system. Background technique [0002] With the rapid development of computer technology, image processing technology, and machine learning technology, the application fields of computer vision continue to expand. Among them, abnormal behavior detection is an important branch, which aims to detect the behavior status of people by analyzing the behavior of people in the surveillance video, so as to carry out risk assessment and emergency response. widely used. [0003] For the identification of abnormal behavior based on surveillance video, in the early stage, it mainly relied on the naked eye observation and identification of surveillance personnel, or looked back at the video to collect evidence after the accident, which was inefficient. With the development of computer vision and artifici...

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): G06K9/00G06T7/254G06T7/66
CPCG06T7/254G06T7/66G06V40/20G06V20/40G06V20/52
Inventor 王德强王鸣天郑来波焦广超李晓
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products