Supercharge Your Innovation With Domain-Expert AI Agents!

T gait cycle detection method based on a convolutional neural network

A convolutional neural network and periodic detection technology, applied in the field of computer vision, can solve problems such as large errors and achieve strong robustness

Active Publication Date: 2019-05-17
HARBIN ENG UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Higher recognition rate was obtained in side 90°, front and back viewing angles, but errors were larger in oblique viewing angles such as 18° and 36°

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
  • T gait cycle detection method based on a convolutional neural network
  • T gait cycle detection method based on a convolutional neural network
  • T gait cycle detection method based on a convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Taking a large-scale gait recognition database as an example, the gait database contains gait video sequences of 124 people, each with 110 videos, including different viewing angles, clothing and objects.

[0043] Step 1. Preprocessing the gait video, including image preprocessing operations such as video decoding, pedestrian contour extraction and centroid normalization. First of all, the video sequence should be divided into frames. After the frame division, the sequence is an orderly sequence of images arranged in chronological order. The image sequence containing pedestrians and the background sequence are first subjected to grayscale transformation. As far as the environment is concerned, the median method can be used to estimate the background of the entire sequence, and then the background image is subtracted from the foreground image and then binarized to obtain the gait contour image. Let The gray value is I k (x,y), where the background gray value is M k (x,...

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 provides a gait cycle detection method based on a convolutional neural network, and the method comprises the steps: carrying out the preprocessing of a gait video, and comprises the image preprocessing operation: video decoding, pedestrian contour extraction, and centroid normalization; Training a convolutional neural network used for extracting gait periodic features; And sending the gait video frame sequence to be detected into a convolutional neural network, and after filtering an output waveform, determining the positions of adjacent wave crests and wave troughs to obtain a gait period. Angle change of the method, the change of clothes and carried objects has very high robustness; The gait cycle detection method solves the problem that the gait cycle is difficult to detect under front and back visual angles, is of great significance for improving the gait recognition precision in a complex environment, can be used at the front end in gait recognition, and is suitablefor identity recognition in safety monitoring, man-machine interaction, medical diagnosis, access control systems and the like.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a gait cycle detection method based on a convolutional neural network. Background technique [0002] Compared with biometric identification, gait recognition can complete data collection and long-distance identification without the knowledge of the tester. Gait cycle detection is an inevitable process in gait recognition, and a gait recognition algorithm with a good recognition rate is based on a well-segmented gait cycle. And because gait recognition has the characteristics of concealment, the data collection is relatively random. The direction of pedestrians relative to the camera and the state of clothing of pedestrians can be arbitrary, which increases the difficulty of periodic detection. [0003] The development of gait cycle detection technology is accompanied by the development of gait recognition. In the existing methods, most of the pedestrian width is used ...

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): G06K9/00G06N3/04G06N3/08
Inventor 王科俊丁欣楠李伊龙周石冰徐怡博
Owner HARBIN ENG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com