Adult gait extraction and anomaly analysis method based on Kinect

An analysis method and gait technology, applied in the field of computer vision and biometric recognition, can solve the problem of lack of analysis of joint posture changes

Active Publication Date: 2018-12-07
UNIV OF JINAN +1
View PDF7 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, most of the above methods only record the position coordinates of human joints in three-dimensional space, and extract gait features accordingly, lacking the analysis of the posture changes of joints in three-dimensional space

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
  • Adult gait extraction and anomaly analysis method based on Kinect
  • Adult gait extraction and anomaly analysis method based on Kinect
  • Adult gait extraction and anomaly analysis method based on Kinect

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The invention aims to use the Kinect sensor to obtain various gait parameters of adults when they walk naturally, analyze the adult walking sampling data based on the knowledge of probability theory and mathematical statistics, obtain the normal range of each parameter, and provide guidance for doctors' clinical analysis.

[0038] The present invention extracts the natural gait of an adult based on Kinect (2.0), and sets the entire experimental environment as an indoor environment. Since the effective measurement distance of Kinect (2.0) is 0.5 to 4.5 meters, and the resolution will decrease slightly with the increase of the measured distance, the subjects should not be too far away from Kinect. In addition, due to the limited viewing angle range of Kinect, the placement of Kinect too high or too low from the ground, or to the left or to the right will cause the subject to not be completely presented in the field of vision. Considering the above factors, and in order to...

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

An adult gait extraction and anomaly analysis method based on Kinect mainly comprises the following steps of: (1) collecting adult traveling videos, and solving and obtaining adult traveling gait space-time parameters based on foot end track analysis and lower limb inverse kinematics; (2) performing deduction based on the lower limb inverse kinematics to calculate Z-Y-X Euler angles and step lengths of hip joints, knee joints and ankle joints of an adult; (3) calculating the maximum value, the minimum value, the mean value and the variance of each joint angle in each set of data to obtain datacomprising the joint angles, the step lengths and the gait time parameters; and (4) employing a K-S single simple to inspect and obtain distribution conditions of the parameters, and combining the Pauta criterion to obtain the normal ranges of the parameters. On the basis of collection of adult gait parameters, small samples are analyzed based on the related knowledge of the probability and mathematical statistics to obtain the normal ranges of the parameters and provide reference for doctors' clinical analysis.

Description

technical field [0001] The invention relates to a clinical analysis method for extracting gait parameters of adults' natural walking based on a Kinect sensor and applying it to abnormal gait, and belongs to the field of computer vision and biological feature recognition. Background technique [0002] Gait refers to a periodic form and appearance of people or animals moving forward through limb movements (such as walking, running, foot movement, etc.). Most contemporary research on gait analysis focuses on human beings, so when "gait" is mentioned, it generally refers to human behavior. Gait is completed by the human body through a series of activities of the pelvis, hips, knees, ankles and toes under the control of the central nervous system. Therefore, whether the gait is normal is of great significance to measure the health of the human body. [0003] The existing adult walking data acquisition and gait extraction methods are divided into three types: the first one is to ...

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
CPCG06V40/25G06V10/462
Inventor 张勤郭佳旻柴汇李贻斌
Owner UNIV OF JINAN
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