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

Monitoring method and system for recognizing hanging behavior

A monitoring system and behavior technology, applied in the field of image processing, can solve the problems of manpower consumption, analysis, and failure to detect hanging behavior in time, so as to prevent false alarms and reduce operations

Inactive Publication Date: 2013-05-08
TELEFRAME TECH BEIJING
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the current general monitoring equipment cannot analyze the behavior in the video scene, installing a large number of cameras requires more manpower to monitor a large number of videos in real time. Obviously, this is more manpower-intensive, and in the actual situation, there is not enough manpower. Tired of monitoring a large number of videos in real time, it is impossible to respond to such extreme behavior as hanging
[0006] In summary, the monitoring methods in the prior art cannot detect the occurrence of hanging behavior in time

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
  • Monitoring method and system for recognizing hanging behavior
  • Monitoring method and system for recognizing hanging behavior
  • Monitoring method and system for recognizing hanging behavior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Embodiment 1 of the present invention provides a monitoring method for identifying hanging behavior, such as figure 1 As shown, the steps include:

[0055] Step S110: using the frame difference method to extract the foreground from the current frame image acquired in real time.

[0056] To perform foreground detection, a background image needs to be determined, and then each frame image is differentiated from the background image, and then binarized to obtain a binary image.

[0057] In this embodiment, the first frame of image to be captured by the camera and stabilized may be used as the background image.

[0058] Binarizing the difference image means that the obtained binary image has only two function values. For example, if there is a moving target on the obtained binary image, the function value at the position corresponding to the moving target on the binary image is equal to is the first value, and other positions of the binary image except the position corres...

Embodiment 2

[0075] Embodiment 2 provides a monitoring method for identifying hanging behavior, and the main processing steps include:

[0076] Step S210: Foreground detection is performed on the current frame image acquired in real time by the frame difference method.

[0077] In this embodiment, the frame difference method described in Embodiment 1 is used for foreground detection, and a mixed Gaussian background model, SACON (SAMPLE CONSENSUS), etc. may also be used, which are not listed in this embodiment.

[0078] Preferably, the frame difference method is used for foreground extraction, with the first frame image as the background image, starting from the second frame image, each frame image and the background are differentiated on the three channels of R, G, and B. For each pixel, if the maximum value of the difference results on these three channels is greater than the preset threshold, the value of this point is assigned a value of 255 on the grayscale image, otherwise it is assig...

Embodiment 3

[0109] Embodiment 3 provides a monitoring system for identifying hanging behavior, see figure 2 As shown, it includes a foreground detection module, a contour finding module, a calculation circumscribing rectangle module and an alarm module.

[0110]The foreground detection module is used to extract the foreground using the frame difference method for the current frame image acquired in real time; the contour search module is used to obtain the contour of the human body in the current frame image and store it in the form of a point sequence; the calculation external The rectangle module is used to calculate the circumscribed rectangle of the outline; the alarm module is used to judge whether it is a hanging behavior based on the motion trajectory of the circumscribed rectangle obtained from multiple frames of images, and if so, alarm.

[0111] Preferably, in this embodiment, a filtering module is also included; the filtering module is used to filter out the objects whose size...

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 relates to the image processing technical field, in particular to a monitoring method and a system for recognizing a hanging behavior. The monitoring method comprises the following steps: using a frame difference method to extract a prospect as to a real time available current frame image; searching the human profile of a current frame image and storing in a form of sequence of points; calculating a circumscribed rectangle of the profile; acquiring a moving track of the circumscribed rectangle based on multiple frame images and judging whether or not the behavior is hanging. If yes, then calling the police. The monitoring system comprises a prospect detecting module, a searching profile module, a calculating circumscribed rectangle module and an alarming module. The prospect detecting module is used for utilizing the frame difference method to extract the prospect; the searching profile module is used for obtaining and storing the profile of human bodies of current frame image; the calculating circumscribed rectangle module is used for calculating the circumscribed rectangle of the profile; the alarming module is used for judging whether or not the behavior is hanging based on the moving track of the circumscribed rectangle, if yes, then call the police. The monitoring method and the system for recognizing hanging behavior can timely alarm the hanging behavior.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a monitoring method and system for identifying hanging behavior. Background technique [0002] In recent years, with the development of computer vision and image processing technology, sports human behavior analysis has attracted extensive attention due to its wide application prospects. At present, the visual analysis of human motion is one of the most active research topics in the field of computer vision. Its core is to use computer vision technology to detect, track and recognize people from image sequences and understand and describe their behavior. [0003] In real life, there are many occasions where it is necessary to install a camera to record and monitor what is happening in the monitored area. In special places such as prisons and detention centers, in order to achieve better management of the behavior of prisoners, it is also necessary to install video camer...

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): G06K9/00G06K9/54
Inventor 王海峰刘忠轩
Owner TELEFRAME TECH BEIJING
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com