Novel method and device for safety supervising of human body moving target video frequency detection

A technology of human motion and target video, applied in the field of human motion target video detection, to achieve the effect of powerful real-time processing capability, good scalability, and good equipment

Inactive Publication Date: 2008-08-27
JIANGSU WISCOM TECHNOLOGY CO LTD +1
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Technical problem: This invention patent invents a reliable video detection method and device for human moving objects in complex environments and scenes, which can eliminate the effects of light changes in the env

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
  • Novel method and device for safety supervising of human body moving target video frequency detection
  • Novel method and device for safety supervising of human body moving target video frequency detection
  • Novel method and device for safety supervising of human body moving target video frequency detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] 1. Principles and methods

[0021] As shown in Figure 1, the system first collects a sequence of images as historical images for background reconstruction, and then performs foreground extraction, binarization processing, opening and closing operations, and labeling operations on the current frame. The torque conversion technology performs human body recognition, and finally uses the preset safety rules to calculate the abnormal behavior of the person, thereby sending out an alarm message. The main steps are as follows:

[0022] a) Background reconstruction

[0023] In a complex environment, due to periodic changes in the environment, such as tree shadows shaking, simple frame difference method to extract targets will cause large errors. This invention uses a Gaussian model to reconstruct the background, which can eliminate these periodic factors.

[0024] The pixel grayscale change in the color sequence image can be regarded as a random process with noise. In the bac...

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 novel and reliable method used for detecting a video of human moving target and a device thereof, which accurately identifies a human moving target by using a technology of dynamic cluster and moment invariants based on human body models, monitors the behavior of a human body according to a preset safety regulation and sends out an alarm. The device adopts TMS320DM6446 as a platform of core software and hardware, a high-performance dual-core structure and a platform tool of a chip guarantee that the device not only has a powerful capability of real-time processing, but also has an excellent function of peripheral management. The device can be used in the prior video monitoring system, and has strong universality and advancement for application.

Description

technical field [0001] The patent of the present invention is to invent a new method and device for video detection of human moving objects for security monitoring, which is used in a security video monitoring system. Background technique [0002] Monitoring, tracking, identifying and alarming human moving targets in complex environments and scenes is very important for the safety management of buildings, industrial equipment and public places. At present, the method used in the video surveillance system is basically a simple moving object detection method based on the frame difference method, and the moving object is obtained by using the difference between adjacent frames of the sequence image, and compared with a certain area sensitivity threshold set in advance, so as to obtain Whether there is a moving target in the area. This method, while simple, is not reliable. The actual environment is more complex, such as changes in light, swaying tree shadows, flying birds, et...

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
IPC IPC(8): G08B13/196
Inventor 陆永刚黄健元张长顺张雪峰赵瑶池杨维娟
Owner JIANGSU WISCOM TECHNOLOGY CO LTD
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