Pedestrian tracting method based on principal axis marriage under multiple vedio cameras

A multi-camera, pedestrian tracking technology, applied in the field of computer vision, to achieve the effect of good application prospects

Inactive Publication Date: 2007-04-04
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF0 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, how to select more robust and acc

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
  • Pedestrian tracting method based on principal axis marriage under multiple vedio cameras
  • Pedestrian tracting method based on principal axis marriage under multiple vedio cameras
  • Pedestrian tracting method based on principal axis marriage under multiple vedio cameras

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The main features of the present invention are: 1) Extracting the main axis of a person as a matching feature. Since the main axis of the human body is the symmetry axis of the human body area, according to the symmetry, the points symmetrically distributed on both sides of the main axis will cancel out their errors, thus making the main axis more robust. And the human axis is less affected by the results of motion detection and segmentation; 2) Three detection methods for the human axis in different situations are proposed: the axis detection of a single person, the axis detection of a group of people, and the human axis under occlusion The detection of the main axis; 3) Based on the geometric relationship constraints of the main axes under different viewing angles, the main axis matching likelihood function is defined to measure the similarity of the main axis pairs under different viewing angles; 4) According to the matching results, the multi-view information is fuse...

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 method comprises: making motion detection for sequence image; extracting the feature of main axis; making trace under single video camera; according to the main axis matching function, building main axis matching pair; combining multi view angles information to optimize and renew the trace result.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a multi-camera matching method. Background technique [0002] With the development of society, safety issues are becoming more and more important. Visual surveillance has become a requirement in many large venues. These places include important national security departments and military. At the same time, in many public places, visual monitoring has become crucial, and a typical application is the field of traffic. Since the traditional visual monitoring system is a kind of post-event monitoring, all accidents and abnormal situations are discovered by the security personnel at the time or after the event, and cannot prevent various behaviors that undermine security; therefore, the traditional monitoring system will Can not meet the needs of social development. At this time, an intelligent visual surveillance system has become the requirement of the times and the goal ...

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): H04N5/232G06T7/60G06T7/00G06F17/00A61B5/117
Inventor 胡卫明周雪胡敏
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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