Pedestrian re-identification method based on fusion ranking optimization of similarity and dissimilarity

A pedestrian re-identification and sorting optimization technology, applied in character and pattern recognition, biometrics recognition, instruments, etc., can solve problems such as unsatisfactory optimization results

Active Publication Date: 2017-07-11
WUHAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Among them, the existing pedestrian re-identification technology based on optimal ranking only uses similarity but not dissimilarity, and its optimization results are not ideal

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 re-identification method based on fusion ranking optimization of similarity and dissimilarity
  • Pedestrian re-identification method based on fusion ranking optimization of similarity and dissimilarity
  • Pedestrian re-identification method based on fusion ranking optimization of similarity and dissimilarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0053] The present invention is a pedestrian re-identification method based on similarity and dissimilarity fusion sorting optimization; optional ELF method, SDALF method, LDFV method, SDC method, BiCov method, SCND method, PCCA method, PRDC method, LMNN method, Two methods in the ITML method, the KISSME method and the FPM method (hereinafter referred to as method 1 and method 2) perform similarity and dissimilarity fusion ranking optimization;

[0054] First, get the initial sorting results based on method 1 and method 2; then take the intersection of the fi...

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 pedestrian re-identification method based on fusion and ranking optimization of similarity and dissimilarity. Pedestrian re-identification is a retrieval problem for specific pedestrians. are similar to the extremely positive samples of , and are not similar to the extremely negative samples of the query pedestrian. At the same time, we define those pedestrians who are similar to extremely positive samples as suspected positive samples, and samples similar to extremely negative samples are suspected negative samples. By improving the ranking of suspected positive samples and reducing the ranking of suspected negative samples, we can achieve the optimization of way to improve the effect of pedestrian re-identification. Furthermore, the results of multiple methods are fused to strengthen this similarity and dissimilarity relationship. The present invention further improves the matching accuracy of the same pedestrian under multiple cameras by fusing the sorting results of similarity and dissimilarity.

Description

technical field [0001] The invention belongs to the technical field of surveillance video retrieval, and relates to a pedestrian re-identification method, in particular to a pedestrian re-identification method based on fusion and sorting optimization of similarity and dissimilarity. Background technique [0002] In the actual video investigation, investigators need to quickly check, track and lock the suspected target according to the moving pictures and trajectories of the designated pedestrian object under the multi-camera. The best time to solve the case. Pedestrian re-identification is a cross-camera surveillance video automatic retrieval technology for specific pedestrian objects, that is, matching the same pedestrian object under multiple cameras with no overlapping illumination areas. This technology is used to assist video investigators to quickly and accurately discover the moving pictures and trajectories of suspected targets, which is of great significance for th...

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): G06F17/30G06K9/00
CPCG06V40/23G06V40/10
Inventor 胡瑞敏叶茫梁超刘俊王正陈军阮威健
Owner WUHAN UNIV
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