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

Gait recognition method based on average differential image

A gait recognition, differential image technology, used in character and pattern recognition, instruments, computer parts, etc.

Inactive Publication Date: 2018-11-16
TIANJIN UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The biggest disadvantage of this method is that it ignores the movement characteristics of the limbs and torso of various parts of the human body during walking, and the movement characteristics of the human torso can just reflect the characteristics of human walking.

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
  • Gait recognition method based on average differential image
  • Gait recognition method based on average differential image
  • Gait recognition method based on average differential image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Due to the limitations of current image processing technology, the current gait recognition algorithm can only be applied to gait recognition in the case of a single person walking past the camera in a fixed background. The specific implementation steps of the present invention are as follows (see figure 1 ):

[0033] Step 1 Image Framing: Divide the video image into individual frames (see figure 2 ).

[0034] Step 2 Image preprocessing: In order to avoid the influence of noise points on the image, Gaussian blurring is first performed on each frame of image. The size of the Gaussian blur radius can be selected from 2-4 pixels.

[0035] Step 3 Calculation of the background template. Suppose there are a total of N images, and the gray value of the point whose coordinates are x and y in the i-th image is b i (x, y), then the gray value of point x, y in the background template is defined as the background value of the most frequently occurring gray value of the point ...

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 relates to a gait recognition method based on an average differential image, which is applied to gait recognition in a fixed background when a single person walks pass a camera successively. The method comprises following steps: image framing is carried out; a background image is obtained; the contour of a human body is extracted; after each frame of human body contour binary image is subjected to edge clipping, the centroid of each frame of contour is calculated, centroid alignment is carried out, and a centroid alignment contour is obtained; a walking cycle is calculated; in view of the centroid alignment contour in each walking cycle, a differential image between adjacent two frames is calculated; the differential images in multiple walking cycles are overlapped, an average value is obtained, and an average differential image is obtained; features of the average image are extracted; a principal component analysis method is used to calculate the feature value of each average image, the feature values are sorted by absolute values from large to small, and former d feature values with the maximum absolute value are obtained to form a feature vector; and through a nearest neighbor algorithm, gait recognition is carried out.

Description

technical field [0001] The invention belongs to the field of image processing and video monitoring, uses video monitoring at a 90-degree angle to the walking direction of the human body for individual identification, and analyzes the difference between two adjacent frames of images in the video monitoring to construct an average difference image and characterize the average difference image extracted for identification purposes. Background technique [0002] With the popularization of informatization, more and more cities have realized digital urban management, and video surveillance equipment has been installed at important intersections and locations. In the manual way, more manpower is required to monitor each video terminal one by one for real-time target tracking. If a breakthrough is made in gait-based identification research, technically, automatic retrieval and real-time automatic tracking of specific targets can be realized, and an automatic alarm function can also...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/46
CPCG06V40/25G06V10/44
Inventor 陈锦言孙雪莹
Owner TIANJIN 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