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

A method of target re-identification in multi-camera surveillance network

A monitoring network and multi-camera technology, applied in character and pattern recognition, image communication, computer components, etc., can solve the problem of low target recognition rate

Inactive Publication Date: 2018-02-16
XIAN UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a method for target re-identification in a multi-camera monitoring network, which solves the problem in the prior art that the target recognition rate is low due to the lack of full use of the correlation of each image in the image data set

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
  • A method of target re-identification in multi-camera surveillance network
  • A method of target re-identification in multi-camera surveillance network
  • A method of target re-identification in multi-camera surveillance network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0091]The principle on which the present invention is based is: in actual life observation, the human eye can always accurately find the matching target in the data set, because the human eye has extracted the salience that can distinguish the target to be recognized from other targets. feature, the salient feature is highly robust to target deformation, viewing angle changes, and different lighting scenes; it can find the only optimal matching result of the target in the data set and distinguish it from other results. Intuitively, assuming that an object has certain salient regions in one camera, then when the object reappears in the field of view of other cameras, it should also have corresponding salient regions.

[0092] A method for target re-recognition in a multi-camera monitoring network of the present invention first uses visual atte...

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 a method for target re-identification in a multi-camera monitoring network, comprising the steps of: selecting image sequences of N pairs of targets between cameras i and j, and recording them as test image sequences and reference image sequences; obtaining camera i and camera The brightness transfer function between j; use the brightness transfer function to correct the color of the test image to be recognized to the same level as the reference image sequence; extract the ColorSIFT feature of each image in the test image to be recognized and the reference image sequence respectively and perform feature search and matching, and then according to KNN According to the saliency map and ColorSIFT feature, the two-way similarity is calculated, and the reference image corresponding to the maximum similarity is used as the matching target of the test image to be recognized, and the target is recognized. The method for target re-identification in a multi-camera monitoring network of the present invention solves the problem in the prior art that the target recognition rate is low due to insufficient utilization of the correlation of each image in the image data set.

Description

technical field [0001] The invention belongs to the technical field of machine vision and relates to a method for re-identifying targets in a multi-camera monitoring network. Background technique [0002] In a multi-camera monitoring and tracking network, due to too many uncertain factors of the tracked target, such as monitoring angle of view, ambient light, and target pose changes, how to re-identify the target is a difficult point. In recent years, many methods have been proposed for the problem of cross-view target tracking. During cross-view target tracking, the non-overlapping areas between cameras lead to tracking discontinuity. After the tracked target crosses the "blind zone" between cameras, the Its accurate re-identification, that is, how to build a robust appearance feature model, is a challenging problem. Extracting a robust appearance statistical feature is the core of the object re-identification problem. [0003] Therefore, someone proposes an appearance mo...

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 Patents(China)
IPC IPC(8): G06K9/00H04N7/18
CPCH04N7/181G06V20/40G06V2201/07G06F18/22
Inventor 刘龙王攀郑丽
Owner XIAN UNIV OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com