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

Pedestrian re-identification method based on attitude normalized image generation

A pedestrian re-identification and image generation technology, which is applied in biometric recognition, neural learning methods, character and pattern recognition, etc., can solve the problems of appearance changes without generalization ability, and achieve good scalability and generalization ability , to achieve the effect of feature complementation and removal of attitude interference

Active Publication Date: 2018-09-14
FUDAN UNIV
View PDF5 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method also does not have a good generalization ability for appearance changes caused by gestures.

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 attitude normalized image generation
  • Pedestrian re-identification method based on attitude normalized image generation
  • Pedestrian re-identification method based on attitude normalized image generation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The specific implementation of the present invention is mainly introduced with 4 modules, which correspond to the total 4 parts of the content of the invention and the comprehensive invention process respectively. The details are as follows:

[0033] 1. The average posture and attribute characteristics of pedestrians

[0034] For the prediction of attribute features, the present invention defines 26 attribute numbers, and directly applies the attribute prediction model [4] to all training data and test data, and the predicted attribute feature dimension is 1×26. In order to make the dimension of the attribute feature consistent with the dimension in the pose normalized image generation model, 1×26 is mapped to 2×1×52. First, 0 in the attribute dimension is mapped to 01, and 1 is mapped to 10, then 1×26 can be mapped to 1×52; then, the 52-dimensional attribute features are copied and stitched together, that is, mapped from 1×52 to 2×1×52; for pose estimation, directly u...

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 belongs to the technical field of computer image recognition, and specifically relates to a pedestrian re-identification method based on attitude normalized image generation. The methodcomprises steps of: predicting a pedestrian average attitude and attribute features; constructing, training and testing an attitude normalized image generation model and generating eight pedestrian images having different attitudes; constructing, training and testing pedestrian re-identification feature extraction network to obtain a pedestrian re-identification feature; and finally, performing the pedestrian re-identification feature fusion, and obtaining the features of a pedestrian target to be detected and all candidate pedestrian targets. The method of the invention has the advantages ofhigh speed, high precision, good robustness, good generalization ability and good expandability, and is very suitable for practical applications such as video pedestrian monitoring and video pedestrian information retrieval.

Description

technical field [0001] The invention belongs to the technical field of computer image recognition, and in particular relates to a pedestrian re-recognition method based on gesture normalized image generation. Background technique [0002] The pedestrian re-identification task aims to identify and match pedestrians through two disjoint cameras. The appearance of pedestrians can change dramatically due to changes in posture, illumination, occlusion, viewing angle and other factors, which also brings severe challenges to the problem of pedestrian re-identification. Among these influencing factors, the changes brought about by attitude factors are the most direct, obvious, and particularly important. [0003] On the one hand, with the upsurge of deep learning, more and more computer vision tasks have begun to be solved using deep learning methods, including pedestrian re-identification tasks. The deep learning methods proposed in recent years to solve pedestrian re-identificat...

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
CPCG06N3/08G06V40/10G06V20/54G06F18/253
Inventor 付彦伟钱学林薛向阳王文萱姜育刚
Owner FUDAN 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