Gait cycle detection method through layering and coding for depth information

A layered encoding and depth information technology, which is applied in the fields of image processing and pattern recognition, can solve the problems of not being able to make full use of the grayscale features of depth images, and it is difficult to detect gait cycles in depth sequence images, and achieve high accuracy.

Inactive Publication Date: 2015-02-18
SHANDONG UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods are all for gait video streams, it is difficult to directly transplant to gait cycle detection on depth sequence images, and cannot make full use of the grayscale features of depth images

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 cycle detection method through layering and coding for depth information
  • Gait cycle detection method through layering and coding for depth information
  • Gait cycle detection method through layering and coding for depth information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] Select the cut depth image sequences of two different research objects in the TUM GAID database, respectively as image 3 , 4 As shown, places of different colors represent different depth intensity values.

[0037] The uniform threshold was chosen experimentally. Use I(m,n) to represent the gray intensity at the pixel point coordinates (m,n) in the original depth image, and Bw(m,n) to represent the quantized coding value of the pixel point after layered processing. The specific selection is:

[0038] ① The gray value is quantized into 2 layers:

[0039] Bw ( m , n ) = 0 I ( m , n ) = 0 ...

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 gait cycle detection method through layering and coding for depth information. According to the method, depth sequence information is transformed into depth features of single frames to analyze problems, that is, the gait cycle is analyzed according to layer feature change conditions of depths of images in each frame. The detection method comprises the steps of extracting gray values of single frame depth images after background removal; subjecting the gray value information of single frame depth images after background removal to layering according to a set threshold; performing uniform quantization coding on each layer of information; calculating the sum of pixel codes of each frame to form new signals; and separating the gait cycle according to minimal value points of the new signals. According to the detection method, the gray features of the depth images are fully used, the accuracy of the separated gait cycle is high, a certain foundation is laid for accurate gait recognition.

Description

technical field [0001] The invention relates to the fields of image processing and pattern recognition, in particular to a gait cycle detection method for layered encoding of depth information. Background technique [0002] With the rapid development of computer storage and coding technology, depth information is getting more and more attention in the fields of computer vision and image processing. Different from two-dimensional optical images, each pixel in the depth image represents a relative depth information, through which the surface geometry of the object is described. Compared with traditional optical images, depth images are not affected by ambient lighting and shadows, which greatly improves data reliability. [0003] In the field of gait recognition, the use of depth data for identity recognition is also gaining attention. Gait recognition is to obtain the gait characteristics of the researched object from the walking posture of people to identify the individual...

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): A61B5/117A61B5/11G06K9/00
Inventor 贲晛烨张鹏江铭炎付希凯陆华葛国栋
Owner SHANDONG 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