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

Motion recognition method and system

A motion recognition and motion technology, applied in the field of motion recognition analysis, can solve the problems of low recognition accuracy and accuracy, no effective use of motion trajectory feature information, and inability to recognize complex motion trajectories, so as to improve the recognition accuracy and accuracy. Effect

Active Publication Date: 2015-02-18
SUZHOU UNIV
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, most motion recognition methods use various means and tools such as Euclidean distance, trajectory profile description and various transformation functions. However, due to the lack of effective use of the feature information of the motion trajectory, complex motion trajectory In some cases, these methods cannot be accurately identified, resulting in low recognition accuracy and accuracy, and sometimes even complex motion trajectories cannot be identified

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
  • Motion recognition method and system
  • Motion recognition method and system
  • Motion recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 7

[0113] In order to facilitate those skilled in the art to better understand the technical solutions provided by the present invention, based on the technical solutions disclosed in the above embodiments, and aiming at the actual application process, the present invention provides Embodiment 7 of a motion recognition method, including:

[0114] Step S800, calculating the curvature k and torque τ of each point on the motion track;

[0115] Step S801, obtain the first-order derivative k of the curvature and torque parameters of each trajectory point with respect to the arc length s and τ s ;

[0116] The representation of a 3D motion trajectory is:

[0117] Γ(t)={X(t),Y(t),Z(t)|t∈[1,N]}

[0118] Among them, Γ represents the motion trajectory, t is the time of each frame of image, N represents the length of the trajectory, that is, the time of the last stitch image, where N is a natural number; it should be noted that N here is also the number of trajectory points;

[0119] In...

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 motion recognition method and system. The motion recognition method comprises the steps that N track points on a motion track are obtained; the descriptor of each track point is determined, wherein the descriptor comprises the motion category and the scale level; the descriptors of the N track points are ranked, and a descriptor sequence of the motion track is obtained; the motion type of the motion track is determined by means of the descriptor sequence of the motion track, and therefore motion recognition is completed. According to the technical scheme, feature information of the motion track is effectively utilized, and then the recognition precision and accuracy rate are improved.

Description

technical field [0001] The invention relates to the technical field of motion recognition and analysis, in particular to a motion recognition method and system. Background technique [0002] With the rapid development of social science and technology, more and more occasions such as video surveillance, automatic monitoring and recognition, and human-computer interaction need to use trajectory-based motion recognition. [0003] At present, most motion recognition methods use various means and tools such as Euclidean distance, trajectory profile description and various transformation functions. However, due to the lack of effective use of the feature information of the motion trajectory, complex motion trajectory In some cases, these methods cannot be accurately identified, resulting in low recognition accuracy and accuracy, and sometimes even complex motion trajectories cannot be identified. Contents of the invention [0004] In view of this, the present invention provides...

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): G06T7/00G06K9/66
CPCG06T2207/30241
Inventor 杨剑宇徐浩然胡大盟
Owner SUZHOU UNIV