Pedestrian re-identification method based on sparse attention network

A recognition method and attention technology, applied in the field of computer vision, can solve problems such as loss of effective features

Active Publication Date: 2019-11-05
GUANGXI NORMAL UNIV
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] What the present invention aims to solve is the problem that the existing pedestrian re-identification method loses a large number of effective features when performing deep learning, and provides a pedestrian re-identification method based on sparse att...

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 sparse attention network
  • Pedestrian re-identification method based on sparse attention network
  • Pedestrian re-identification method based on sparse attention network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific examples.

[0052] The pedestrian re-identification model constructed by the present invention is a sparse normalized compression-excitation network, such as figure 1 As shown, it is mainly composed of a backbone layer in the middle, 4 short connections on one side of the backbone layer, and 4 normalized compression-excitation modules on the other side of the backbone layer.

[0053] (1) Backbone layer:

[0054] The first convolutional layer, the convolutional layer is composed of filters with a kernel size of 7×7, which is used for dimensionality reduction. After dimensionality reduction, the image becomes 1 / 4 of the original image size, so this layer is mainly to reduce Calculations.

[0055] The second layer is the maximum pooling layer, that is, the maximum value is taken in th...

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 a sparse attention network. The pedestrian re-identification method comprises the following steps: firstly, transmitting shallowfeatures to deep features in a lossless manner through short connection; secondly, extracting a main volume and features of the image through a trunk residual network formed by continuously superposedresidual modules; extracting detail features, which are liable to be lost, of the image through a normalized compression-excitation module embedded in the backbone residual network; and finally, multiplying the obtained features, adding the features obtained in the first part, and conveying the features into a full connection layer and a classification regression layer to obtain classification and regression results. The sparse attention network can effectively extract pedestrian photo detail features of a plurality of pedestrian re-identification data sets.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a pedestrian re-identification method based on a sparse attention network. Background technique [0002] Pedestrian re-identification refers to re-confirming the identity of the same pedestrian in different monitoring scenes to make up for the visual limitations of a single camera. Pedestrian re-identification can be widely used in intelligent image understanding, intelligent video analysis, intelligent video detection and other fields. At present, the methods applied to pedestrian re-identification are mainly divided into: pedestrian re-identification based on artificial design features and pedestrian re-identification based on deep convolutional neural network. Pedestrian re-identification based on artificial design features mainly includes two parts: artificial design feature extraction and feature similarity measurement; pedestrian re-identification model based on de...

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): G06K9/00G06K9/62
CPCG06V40/10G06F18/2136G06F18/214G06F18/241
Inventor 张灿龙解盛李志欣
Owner GUANGXI NORMAL 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
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