Unsupervised pedestrian re-identification method based on pseudo-label self-correction

A person re-identification, unsupervised technology, applied in the field of computer vision, can solve the problems of relying on pseudo-labels, pseudo-labels being sensitive to noise, etc.

Active Publication Date: 2021-03-16
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method relies heavily on the quality of pseudo-labels, an...

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
  • Unsupervised pedestrian re-identification method based on pseudo-label self-correction
  • Unsupervised pedestrian re-identification method based on pseudo-label self-correction
  • Unsupervised pedestrian re-identification method based on pseudo-label self-correction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0073] In this embodiment, as figure 1 The process shown is implemented. As shown in the figure, an unsupervised pedestrian re-identification method based on pseudo-label self-correction includes the following steps:

[0074] The specific implementation process of step S1 is as follows:

[0075] Construct the source domain dataset, target domain dataset, target domain test set and algorithm model M, and use the source domain dataset to pre-train the algorithm model M. Among them, the step S1

[0076] Construct the source domain dataset: Collect all pedestrian pictures from different surveillance cameras in the source domain scene, and mark each pedestrian picture with a specific pedestrian ID by manual or machine marking. The pedestrian ID corresponding to each pedestrian picture is The label of the pedestrian image, after the labeling is completed, the obtained source domain data set ends with {X s ,Y s ,P s}, where X s Denotes all pedestrian images in the source domain...

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 an unsupervised pedestrian re-identification method based on pseudo-label self-correction, and the method comprises the steps of constructing a source domain data set, a targetdomain data set and a target domain test set, constructing an algorithm model M, carrying out the pre-training of the algorithm model M through employing the source domain data set, and extracting afirst target feature of the target domain data set through employing the algorithm model M; fusing the first target features to obtain second target features, clustering the second target features toobtain pseudo tags, evaluating the quality of the pseudo tags, correcting clusters with poor quality, and taking an obtained result as a pseudo tag repeated training algorithm model M; and extractinga second target feature from the target domain test set by using the algorithm model M and carrying out image matching to obtain a pedestrian re-identification result.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to an unsupervised pedestrian re-identification method based on pseudo-label self-correction. Background technique [0002] Generally speaking, the task of pedestrian re-identification is the process of retrieving the pictures or videos of the pedestrian under different cameras given a picture or a video of a specific pedestrian. Pedestrian re-identification technology can provide effective help for automated surveillance and surveillance video analysis, and greatly improve the efficiency of surveillance video information retrieval. However, the pictures of the same pedestrian under different cameras have differences in clothing, light intensity, occlusion, posture change, picture quality, and so on. This poses a great challenge to the pedestrian re-identification algorithm. At the same time, in public places, a large number of pedestrians wear similar clothes and have sim...

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): G06K9/00G06K9/40G06K9/34G06K9/62G06N3/04
CPCG06V40/103G06V10/267G06V10/30G06N3/045G06F18/23G06F18/24G06F18/214
Inventor 吕建明梁天保林少川莫晚成胡超杰
Owner SOUTH CHINA UNIV OF TECH
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