Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Pedestrian re-identification method based on local high-frequency features and hybrid metric learning

A pedestrian re-identification and metric learning technology, which is applied in the field of pedestrian re-identification based on local high-frequency features and mixed metric learning, can solve the problem of pedestrian target re-identification difficulties

Pending Publication Date: 2020-06-09
XIAN PEIHUA UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is very difficult to completely rely on feature description to solve the problem of pedestrian target re-identification

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 local high-frequency features and hybrid metric learning
  • Pedestrian re-identification method based on local high-frequency features and hybrid metric learning
  • Pedestrian re-identification method based on local high-frequency features and hybrid metric learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] Pedestrian re-identification technology uses computer vision and image retrieval technology to determine whether there are specific pedestrian images in cross-device images or video sequences. In non-overlapping scenes, affected by factors such as lighting conditions, background changes, occlusions, viewing angles, and pose changes, there are great differences in the appearance of the same target under different cameras, and this difference is even greater than that of different individuals with similar clothing. .

[0070] The present invention provides a pedestrian re-identification method based on local high-frequency features and mixed metric learning, which uses a local frequency feature representation method to extract the color and texture feature sets of the target image under the conditions of illumination and viewing angle changes, and uses a sliding window to Describe local details to extract image features, take the maximum probability value of local frequen...

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 local high-frequency features and hybrid metric learning. A local frequency feature representation method is adopted, a color andtexture feature set of a target image is extracted under illumination and visual angle change conditions, a sliding window is adopted to describe local details and extract image features, the maximumvalue of features appearing locally at high frequency is taken as a feature value, and multi-scale feature descriptor cascading is obtained. After subspace dimension reduction, weight coefficients ofa metric learning matrix and a hybrid metric learning matrix thereof are obtained according to the posterior probability of sample occurrence, and finally a similarity degree as a basis for pedestrian re-identification is obtained. According to the invention, the pedestrian appearance features can be used to identify images related to the given pedestrian in a multi-camera monitoring scene, and the method has good application values in the fields of intelligent monitoring, intelligent security, criminal investigation, pedestrian retrieval, pedestrian tracking, behavior analysis and the like.

Description

technical field [0001] The invention belongs to the technical field of information technology and computer vision, and in particular relates to a pedestrian re-identification method based on local high-frequency features and mixed metric learning. Background technique [0002] The problem of using pedestrian appearance features to identify images related to a given pedestrian in a multi-camera surveillance scene is called person re-identification. Through the automatic analysis, detection, identification and tracking of multi-camera surveillance data, it can match pedestrian targets captured by different cameras at different times and locations. In recent years, the problem of pedestrian re-identification has been a research hotspot in video surveillance technology, widely used in intelligent surveillance, intelligent security, criminal investigation, pedestrian retrieval, pedestrian tracking, and behavior analysis. The in-depth research on it has greatly promoted computer v...

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): G06K9/00G06K9/46G06K9/62G06N3/08
CPCG06N3/08G06V40/10G06V10/44G06V10/50G06V10/56G06F18/23G06F18/22
Inventor 赵增辉林青
Owner XIAN PEIHUA 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
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