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

Unsupervised pedestrian re-identification method and device, electronic equipment and storage medium

A person re-identification, unsupervised technology, applied in the fields of artificial intelligence and computer vision, which can solve problems such as domain separation

Pending Publication Date: 2020-12-11
ZHEJIANG LAB
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the embodiment of the present invention is to provide an unsupervised pedestrian re-identification method, device, electronic equipment and storage medium to solve the problem of directly migrating the model trained in the labeled source domain data set to a new application scenario The problem of creating domain gaps

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 and device, electronic equipment and storage medium
  • Unsupervised pedestrian re-identification method and device, electronic equipment and storage medium
  • Unsupervised pedestrian re-identification method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, the embodiment of the present invention discloses an unsupervised pedestrian re-identification method, including the following steps:

[0052] The pre-training step S101 is used to pre-train the deep pedestrian re-identification model in the labeled source domain data set with a supervised learning method;

[0053] In this step, the deep person re-identification model Using a deep residual neural network and supervised training on a labeled source domain dataset, the Obtain relatively robust performance on the source domain.

[0054] The training feature extraction step S103 is used to extract the training features of the training set samples in the unlabeled target domain using the pre-trained deep pedestrian re-identification model ;

[0055] The division step S105 is used to divide the target domain training set samples into several clusters by using adaptive clustering method according to the training features, and assign correspond...

Embodiment 2

[0094] Such as figure 2 As shown, this embodiment provides an unsupervised pedestrian re-identification device, which is a virtual device corresponding to the unsupervised pedestrian re-identification method provided in Embodiment 1, and the device has corresponding functional modules for executing the method and beneficial effects , the device consists of:

[0095] The pre-training unit 901 is used to pre-train the deep pedestrian re-identification model with a supervised learning method in the labeled source domain data set;

[0096] The training feature extraction unit 903 is used to utilize the pre-trained deep pedestrian re-identification model to extract the training features of the training film set samples in the unlabeled target domain;

[0097] The dividing unit 905 is used to divide the target domain training set samples into several clusters by using an adaptive clustering method according to the training features, and assign corresponding pseudo-labels;

[0098...

Embodiment 3

[0103] This embodiment provides an electronic device, including:

[0104] one or more processors;

[0105] memory for storing one or more programs;

[0106] When the one or more programs are executed by the one or more processors, the one or more processors implement the unsupervised person re-identification method as described in Embodiment 1.

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 and device, electronic equipment and a storage medium. The method comprises the steps of pre-training a pedestrian re-identification model in a labeled source domain data set; utilizing the model to extract training features of a training set in a label-free target domain; according to the training features, dividing a target domain training set into a plurality of clusters based on an adaptive clustering method, and allocating corresponding pseudo tags; setting each cluster as a prototype, selecting a sample from theprototypes, the distance between the sample and the center of the prototype being less than a set threshold, and retraining the model by using the training features and the pseudo-tags of the sample to obtain a pedestrian re-identification model after parameter updating; and inputting the query set of the target domain and the to-be-selected set into the model to respectively obtain test featuresof the query set and the to-be-selected set, and selecting a picture meeting the picture query requirement from the to-be-selected set according to the similarity of the test features. According to the invention, the domain interval problem is effectively alleviated, and the accuracy of cross-domain pedestrian re-identification is improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and computer vision, and in particular relates to an unsupervised pedestrian re-identification method, device, electronic equipment and storage medium. Background technique [0002] With the acceleration of urbanization, public safety has become the focus and demand of people's increasing attention. Many important public health areas such as university campuses, theme parks, hospitals, and streets are widely covered with surveillance cameras, creating good objective conditions for automated surveillance using computer vision technology. [0003] In recent years, person re-identification, as an important research direction in the field of video surveillance, has attracted increasing attention. Specifically, pedestrian re-identification refers to the technology of using computer vision technology to judge whether a specific pedestrian exists in an image or video sequence under cro...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/08G06V40/172G06V40/10G06F18/23G06F18/22
Inventor 陆易叶喜勇王军徐晓刚何鹏飞张文广
Owner ZHEJIANG LAB
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