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

Unsupervised pedestrian re-identification method based on self-label refining deep learning model

A technology of pedestrian re-identification and deep learning, applied in the field of unsupervised pedestrian re-identification based on self-label refined deep learning model, to achieve the effect of improving robustness

Pending Publication Date: 2022-06-21
NINGBO UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The problem solved by the present invention is how to correct the pseudo-label through local features, so as to alleviate the difference in the picture of the same pedestrian caused by cross-view angle, and how to optimize the loss function, so as to further improve the robustness of the network to noise labels

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 self-label refining deep learning model
  • Unsupervised pedestrian re-identification method based on self-label refining deep learning model
  • Unsupervised pedestrian re-identification method based on self-label refining deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] This embodiment provides an unsupervised person re-identification method based on a self-label refined deep learning model, such as Figure 1 to Figure 3 As shown, the method includes the steps:

[0043] S1: Get a dataset of pedestrian images without labels where N is the number of pictures in the dataset, x i Represents the i-th pedestrian image in the dataset, adjust the size of each image to the same height and width, and perform preprocessing;

[0044] S2: Build a self-label refined deep learning model, input the preprocessed training data into the network, and extract the multi-granularity features of the picture samples; wherein, the multi-granularity features include global features, upper body features and lower body features;

[0045] S3: Cluster the extracted multi-granularity features to obtain global pseudo-labels, upper-body pseudo-labels and lower-body pseudo-labels;

[0046] S4: Build a memory module according to the clustering result, calculate the c...

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 an unsupervised pedestrian re-identification method based on a self-label refining deep learning model, and relates to the technical field of pedestrian re-identification, and the method comprises the steps: S1, obtaining a pedestrian picture data set without labels, wherein N represents the number of pictures in the data set, xi represents the ith pedestrian picture in the data set, and n represents the number of pictures in the data set; adjusting the size of each picture to be the same in height and width, and performing preprocessing; s2, constructing a self-label refining deep learning model, inputting preprocessed training data into a network, and extracting multi-granularity features of picture samples; wherein the multi-granularity features comprise global features, upper body features and lower body features. According to the method, the pseudo labels can be corrected through the local features, so that the difference of pictures of the same pedestrian caused by cross-view angles is relieved, and the robustness of the network to noise labels is improved.

Description

technical field [0001] The invention relates to the technical field of pedestrian re-identification, in particular to an unsupervised pedestrian re-identification method based on a self-label refined deep learning model. Background technique [0002] Pedestrian re-identification is one of the more popular research directions in the field of computer vision in recent years. It is a problem in image retrieval. It is a technology that uses computer vision technology to determine whether there is a specific pedestrian in an image or video, that is, given a monitored pedestrian image. Retrieve this pedestrian image across devices. [0003] With the development of science and technology, pedestrian re-identification technology has been widely used in intelligent security, video surveillance and other fields. At present, person re-identification has achieved a relatively large breakthrough in the field of labeled supervision, and has shown superior performance. However, since lab...

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 Applications(China)
IPC IPC(8): G06V40/10G06K9/62G06N3/04G06N3/08G06V10/764G06V10/762G06V10/82
CPCG06N3/088G06N3/045G06F18/23G06F18/241
Inventor 余晓婷郭立君张荣
Owner NINGBO UNIV
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