Unsupervised cross-domain pedestrian re-identification method and system

A pedestrian re-identification, unsupervised technology, applied in the field of image recognition, can solve the problems of neglect and full utilization, and achieve the effect of improving the discrimination performance, alleviating the alignment problem and improving the accuracy.

Active Publication Date: 2019-11-05
中科人工智能创新技术研究院(青岛)有限公司
View PDF3 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the inventors discovered during the research and development process that such methods neglected to make full use of large-scale unlabeled data in the target domain.

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 cross-domain pedestrian re-identification method and system
  • Unsupervised cross-domain pedestrian re-identification method and system
  • Unsupervised cross-domain pedestrian re-identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] This embodiment provides an unsupervised cross-domain person re-identification method, please refer to the attached figure 1 , the specific implementation of the method includes the following steps:

[0062] S101. Obtain training image data with identity labels in the source domain and training image data without identity labels in the target domain, and construct a source domain training set with identity labels and a target domain training set without identity labels.

[0063] S102, converting the training image in the source domain to the target domain, and generating image data related to the target domain.

[0064] Specifically, using image conversion technology, the training image data in the source domain training set is converted to the target domain, while ensuring that the identity information of the image in the source domain remains unchanged, thereby generating an image that is similar in style to the image in the target domain and has an identity label in ...

Embodiment 2

[0104] This embodiment provides an unsupervised cross-domain person re-identification system, which includes:

[0105]The training set construction module is used to obtain training image data with identity labels in the source domain and training image data without identity labels in the target domain, and construct the source domain training set and the target domain training set;

[0106] The image conversion module is used to convert the training images in the source domain training set to the target domain to generate image data related to the target domain;

[0107] The initial model training module is used to train an initial pedestrian re-identification model using the generated image data;

[0108] The feature extraction module is used to extract the local features of each training image in the target domain training set based on the trained pedestrian re-identification model;

[0109] The cluster analysis module is used to perform cluster analysis on the training im...

Embodiment 3

[0114] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are implemented:

[0115] Obtain training image data with identity labels in the source domain and training image data without identity labels in the target domain, and construct a source domain training set and a target domain training set;

[0116] Convert the training images in the source domain training set to the target domain to generate image data related to the target domain;

[0117] Use the generated image data to train the initial pedestrian re-identification model;

[0118] Based on the trained pedestrian re-identification model, extract the local features of each training image in the target domain training set;

[0119] Using the extracted local features, cluster analysis is performed on the training image data in the target domain training set;

[0120] Determine the optimal training sam...

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 cross-domain pedestrian re-identification method and an unsupervised cross-domain pedestrian re-identification system. The method comprises the following steps:constructing a source domain training set and a target domain training set; converting the training images in the source domain training set into a target domain, and generating image data related tothe target domain; training an initial pedestrian re-identification model by utilizing the generated image data; extracting local features of each training image in the target domain training set based on the trained pedestrian re-identification model; performing clustering analysis on training image data in a target domain training set by using the extracted local features; determining an optimal training sample in the target domain training set based on a clustering analysis result; utilizing the generated image data and the determined optimal training sample to retrain the pedestrian re-identification model, and repeating in sequence until an iteration stop condition is reached to obtain a final pedestrian re-identification model; and obtaining to-be-identified image data in the targetdomain, and identifying the to-be-identified image data by using the finally obtained pedestrian re-identification model.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an unsupervised cross-domain pedestrian re-identification method and system. Background technique [0002] Person re-identification aims to retrieve other images with consistent identity labels across different cameras given an object-of-interest image. Due to the important role of person re-identification technology in practical applications, such as intelligent video surveillance and content-based image retrieval, it has attracted extensive attention from researchers and industries. At present, with the advent of large-scale marked person re-identification datasets, such as Market1501, CUHK, DukeMTMC-reID and RAP, and the rapid development of deep learning technology, the performance of supervised person re-identification has been greatly improved. For example, MGN has achieved recognition performance exceeding that of humans on the Market1501 dataset. However, in p...

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): G06K9/00G06K9/46G06K9/62
CPCG06V20/00G06V10/44G06F18/23G06F18/214
Inventor 谭铁牛王亮张彰李达单彩峰
Owner 中科人工智能创新技术研究院(青岛)有限公司
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