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

Multi-view gait recognition method and system based on mutual learning network strategy

A learning network and gait recognition technology, applied in character and pattern recognition, biological neural network model, image enhancement, etc., can solve problems such as difficult to hide and difficult to disguise gait information, so as to improve recognition ability and overcome low resolution low effect

Active Publication Date: 2020-08-14
SHANDONG UNIV
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

And gait information is difficult to disguise, it is manifested in the whole human body, so it is also difficult to hide

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
  • Multi-view gait recognition method and system based on mutual learning network strategy
  • Multi-view gait recognition method and system based on mutual learning network strategy
  • Multi-view gait recognition method and system based on mutual learning network strategy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 1 As shown, the multi-view gait recognition method based on the mutual learning network strategy of the present embodiment includes:

[0039] S101: Receive pedestrian gait videos from multiple perspectives.

[0040] In a specific implementation, at least two cameras, such as 2 or 3, can be evenly arranged around the pedestrian. In this way, pedestrian gait-related images can be obtained from multiple viewing angles, and the accuracy of pedestrian gait recognition can be avoided due to viewing angles.

[0041] S102: Extract a gait image of a gait cycle from the video, and extract a gait contour map from the gait image.

[0042] In practice, a stationary background is not easy to obtain, so background modeling is required. Commonly used methods for background modeling include mean method background modeling, median method background modeling, Kalman filter model, Gaussian distribution model, etc. This embodiment uses the mean method which is easy to oper...

Embodiment 2

[0085] A kind of multi-view gait recognition system based on mutual learning network strategy of the present embodiment includes:

[0086] (1) Gait video receiving module, which is used to receive pedestrian gait videos of multiple viewing angles.

[0087] In a specific implementation, at least two cameras, such as 2 or 3, can be evenly arranged around the pedestrian. In this way, pedestrian gait-related images can be obtained from multiple viewing angles, and the accuracy of pedestrian gait recognition can be avoided due to viewing angles.

[0088] (2) Gait image and contour extraction module, which is used to extract a gait image of a gait cycle from the video, and extract a gait contour map from the gait image.

[0089] In practice, a stationary background is not easy to obtain, so background modeling is required. Commonly used methods for background modeling include mean method background modeling, median method background modeling, Kalman filter model, Gaussian distribu...

Embodiment 3

[0132] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps in the above-mentioned multi-view gait recognition method based on mutual learning network strategy are realized.

[0133] In this embodiment, the local features and global features of the gait frame set are extracted through the mutual learning network. The mutual learning strategy can make the network more compact, and the horizontal pyramid model is used in combination with the local information and global information of each person for identification, which effectively improves the Ability to recognize some features.

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 field of gait recognition, and provides a multi-view gait recognition method and system based on a mutual learning network strategy. The multi-view gait recognition methodbased on the mutual learning network strategy comprises the following steps: receiving pedestrian gait videos of multiple views; extracting a gait image of a gait period from the videos, and extracting a gait contour map from the gait image; forming a gait frame set from the gait contour map of one gait period according to a gait sequence, and extracting local features and global features of thegait frame set through a mutual learning network; utilizing the horizontal pyramid pool to combine the local features and the global features to obtain fusion features of a gait cycle gait contour map; and utilizing a softmax function to perform classification prediction on the fusion features of the gait contour map of one gait period to obtain a gait recognition result.

Description

technical field [0001] The invention belongs to the field of gait recognition, in particular to a multi-view gait recognition method and system based on a mutual learning network strategy. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Gait is the change in posture that a person exhibits while walking. This change is usually regular, especially the swing of the upper and lower limbs, and the activities of the shoulder joints, hip joints and knee joints. The gait characteristics of each person are its unique attributes, so various information such as identity, gender, age, etc. can be obtained through gait. At present, gait-based identification is the main research content of gait analysis. In modern society, the safety problem of public places is becoming more and more serious, and the related researches on the proposed identity recogn...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06T5/50
CPCG06T5/50G06T2207/20221G06V40/103G06V10/44G06N3/045G06F18/214
Inventor 陈振学王艳春荣学文
Owner SHANDONG 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