Pedestrian re-recognition method based on global feature splicing

A pedestrian re-identification and global feature technology, applied in the field of pedestrian re-identification based on global feature representation, can solve the problems of unattainable, high recognition rate, complex network model, etc., achieves low computational complexity, simple network structure, and improved network performance. Effect

Pending Publication Date: 2020-02-14
HUBEI UNIV OF TECH
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these algorithms cannot achieve a high r

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-recognition method based on global feature splicing
  • Pedestrian re-recognition method based on global feature splicing
  • Pedestrian re-recognition method based on global feature splicing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0024] This embodiment proposes a feature splicing method of different spatial dimensions, using SE-ResNeXt50 as the basic backbone network, and performing feature splicing on the last three convolutional layers. In order to reduce the lack of information, convolution and global pooling are used to extract deeper features. The extracted features have better fine-grained feature representation capabilities. When measuring the distance, a clustering loss function is used instead of the traditional triplet loss function. During training, random erasing (Random...

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-recognition method based on global feature splicing. The network performance is improved from the spatial dimension. Firstly, an SE-ResNeXt50 network is used asa backbone network to extract pedestrian image features; splicing the features extracted from different convolution layers to enable the feature information to be complementary; finally, convolutionprocessing is conducted on the spliced features again, and features with high fine granularity are obtained, wherein the introduced clustering loss function is different from a triple loss function commonly used at present, and the clustering loss function and the cross entropy loss function are combined to train a model for the first time; according to the method, the recognition effect is basedon a Market1501 data set, two evaluation indexes of Rank-1 and mAP reach 95.9% and 94.6% respectively, the current recognition effect is high, the network structure is simple, and the calculated amount is small.

Description

technical field [0001] The invention belongs to the technical fields of digital image processing and computer vision, and relates to a pedestrian re-identification method, in particular to a pedestrian re-identification method based on global feature representation. Background technique [0002] Person Re-identification, also known as Person Re-identification (Person ReID), refers to judging whether a given pedestrian image exists in a cross-camera environment. The technology is a combination of computer vision, machine learning, and pattern recognition. The specific process is to first extract the features of the query set (Probe) and the candidate pedestrian data set (Gallery), and then sort the similarity according to the feature vectors, which can be used in urban security management, smart retail, photo album clustering and other fields. [0003] Before 2014, researchers identified by designing robust feature extractors and optimized similarity measurement methods. Ho...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V40/103G06V10/44G06F18/241
Inventor 熊炜杨荻椿熊子婕童磊李敏李利荣王娟
Owner HUBEI UNIV OF TECH
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