Person Re-identification Method and Device Based on Residual Attention Mechanism Spatio-temporal Joint Model

A technology of pedestrian re-identification and joint model, which is applied in the field of pedestrian re-identification based on the spatio-temporal joint model of residual attention mechanism, can solve the problem of ignoring the spatio-temporal information of image time series, and achieve the effect of accelerated convergence and high precision

Active Publication Date: 2022-05-13
WUHAN UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the existing methods to solve the pedestrian re-identification problem only use the pedestrian identity information in the tag, and ignore the spatio-temporal information such as the camera ID information, the time sequence of the image, and the frame number of the image in the video, which are easier to collect.

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
  • Person Re-identification Method and Device Based on Residual Attention Mechanism Spatio-temporal Joint Model
  • Person Re-identification Method and Device Based on Residual Attention Mechanism Spatio-temporal Joint Model
  • Person Re-identification Method and Device Based on Residual Attention Mechanism Spatio-temporal Joint Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0053] The embodiment of the present invention provides a pedestrian re-identification method based on the spatiotemporal joint model of the residual attention mechanism. The environment is PyTorch 1.1.0, Python 3.5, CUDA9.0 and CUDNN7.1. During specific implementation, a corresponding environment may be set as required.

[0054] Embodiments of the present invention provide a pedestrian re-identification method based on the residual attention mechanism spatio-temporal joint model, see figure 1 , the implementation process includes the following specific steps:

[0055] In step a, feature extraction is performed on the input pedestrian x through the ResNet-50 model pre-trained by the ImageNet dataset, and the feature matrix is ​​denoted as f.

[0056] Wherein, the ImageNet data set is a public data set, and the ResNet-50 mod...

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 present invention provides a pedestrian re-identification method and system based on the spatio-temporal joint model of the residual attention mechanism, including extracting features of the input pedestrian through the pre-trained ResNet-50 model; constructing a residual attention mechanism network, including the residual attention mechanism module, feature sampling layer, global pooling layer and local feature connection layer; according to the trained residual attention mechanism network, the cosine distance is used to calculate the feature distance and recorded as the visual probability; according to the camera ID and frame in the pedestrian label of the training sample Spatio-temporal probability modeling of number information, and Laplace smoothing for the probability model. Using visual probability and spatiotemporal probability, the final joint spatiotemporal probability is used to obtain pedestrian re-identification results. The invention overcomes the problem that the existing method ignores the time and space prior information in the camera network, optimizes the network iteration with the attention residual mechanism network, accelerates the convergence, and solves the problem through the optimized Bayesian joint probability, so that pedestrians The recognition accuracy is higher.

Description

technical field [0001] The invention belongs to the technical field of pedestrian re-identification, and relates to a pedestrian re-identification method and device based on a residual attention mechanism spatio-temporal joint model. Background technique [0002] Surveillance video is usually unable to obtain very high-quality face pictures due to the camera resolution and shooting angle, and pedestrians often show multi-scale characteristics, making detection and recognition difficult. At this time, pedestrian re-identification has become a very important alternative technology . Pedestrian re-identification is to achieve cross-device retrieval through a given monitored pedestrian image, which can effectively compensate for the visual limitations of fixed-view cameras, and has important application value in the fields of video surveillance, intelligent security, and smart cities. [0003] In recent years, with the development of machine learning theory, methods 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06V40/10G06V10/82G06N3/04
CPCG06V40/10G06N3/045G06V40/23G06V20/46G06V20/52G06V10/454G06V10/82G06F17/18G06V40/103G06F18/2321G06F18/24155
Inventor 邵振峰汪家明
Owner WUHAN 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