Unlock instant, AI-driven research and patent intelligence for your innovation.

A View Invariant Gait Recognition Method Based on Kinect

A technology of gait recognition and perspective, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of complex steps, poor practical applicability, expensive depth camera, etc., and achieve the effect of simple algorithm and strong real-time performance

Active Publication Date: 2019-05-28
SHANDONG NORMAL UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in the current method, changes in illumination, changes in clothing, especially changes in viewing angles, will have a huge impact on the recognition effect
In the 3D-based method, although it is not sensitive to the change of the viewing angle, most of the existing methods mainly face the following two challenges: 1) In the method of using multiple cameras to construct 3D information, due to the need to calibrate the multi-camera , the steps are complicated, and the practical applicability is poor
2) In the 3D method using the depth camera, although the step of camera calibration is omitted, the depth camera used in some methods is expensive and the marketability is poor

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
  • A View Invariant Gait Recognition Method Based on Kinect
  • A View Invariant Gait Recognition Method Based on Kinect
  • A View Invariant Gait Recognition Method Based on Kinect

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] figure 1 Provided the frame diagram of the inventive method, according to shown flow process, comprise following concrete steps:

[0031] (1) Obtain the coordinates of each frame joint point.

[0032] In order to obtain as much information as possible about the position of joint bones in the gait process, we figure 2 Gait data collection and testing are carried out under the experimental environment shown. During the acquisition process, Kinect was placed on a tripod with a height of 1.0 meters, and people walked towards Kinect from a distance of 4.5 meters away from Kinect, as shown by the direction arrow ① in the figure. This direction can ensure that all joint position information is complete and clear retained. When the human body enters the Kinect field of view, we can use the SDK provided by Kinect to automatically save the three-dimensional space coordinates (x, y, z) of the joint position information required for each frame in the walking process in the list...

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 proposes a Kinect-based viewing angle invariant gait recognition method. Taking advantage of the advantage that Kinect can accurately estimate the spatial position information of human joints in real time, it is used as a gait data acquisition device to collect the joint space coordinate information of each frame during walking. The distance between 8 joints is selected as the static feature, the swing angles of the upper and lower limb joints are defined and compared, and a group of angle changes with the best recognition effect is selected as the dynamic feature. The two kinds of features are matched with the template by Euclidean distance and DTW algorithm respectively, and after feature fusion in the matching layer, the nearest neighbor classifier is used to complete the classification and recognition. The algorithm of this method is simple, has strong real-time performance, and has the characteristic of constant viewing angle.

Description

technical field [0001] The invention utilizes the depth information and bone information collected by Kinect to recognize human body gait, and belongs to the field of computer vision and biological feature recognition. Background technique [0002] Gait recognition is an emerging biometric identification method, which is based on the person's walking posture for personal identity verification. Compared with other biometric identification technologies, gait recognition has the characteristics of non-contact, long-distance and difficult to camouflage. According to anatomical research, the differences in physiological structure, different muscle strength, and different bone lengths of each person jointly determine the uniqueness of the human body's gait, which is also the theoretical basis for gait recognition as biometric recognition. Gait recognition technology involves many technical fields such as computer vision and pattern recognition. Due to its advantages and character...

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): G06K9/00G06K9/62
CPCG06V40/25G06F18/24143
Inventor 孙建德王宇飞李静
Owner SHANDONG NORMAL UNIV