Tensor decomposition method for non-equilateral video gesture identification

A technology of tensor decomposition and gesture recognition, which is applied to character and pattern recognition, instruments, computer components, etc., to reduce difficulty, improve accuracy, and improve accuracy

Inactive Publication Date: 2017-03-08
TIANJIN UNIV
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a tensor decomposition method for non-equal-length video gesture recognition that can solve the problem of gesture video sequence recognition and improve the accuracy of video sequence classification

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
  • Tensor decomposition method for non-equilateral video gesture identification
  • Tensor decomposition method for non-equilateral video gesture identification
  • Tensor decomposition method for non-equilateral video gesture identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] A tensor decomposition method for non-equal-length video gesture recognition of the present invention will be described in detail below in conjunction with an embodiment.

[0046] A kind of tensor decomposition method aiming at non-equal-length video gesture recognition of the present invention comprises the following steps:

[0047] 1) Represent an original video as a third-order tensor where I 1 , I 2 and T represent the width, height and video frame number of a video respectively, and I 1 × I 2 Indicates the size of the video frame;

[0048] 2) Perform Tucker decomposition on the third-order tensor Α to obtain a nuclear tensor with reduced dimensions The nuclear tensor of the third-order tensor A Written as follows:

[0049]

[0050] in, u 3 ∈RK×T , let the tensor F=Α× 1 u 1 x 2 u 1 , then the kernel tensor Abbreviated as:

[0051]

[0052] 3) Solve the nuclear tensor, and update the result through dynamic learning until the algorithm conver...

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 tensor decomposition method for non-equilateral video gesture identification. The method comprises the steps of representing an original video as a three-order tensor A, wherein I1, I2 and T represent the width, the height and a video frame number of a video respectively, and I1XI2 represents the size of a video frame; performing Tucker decomposition on the three-order tensor A to obtain a nuclear tensor A' reduced in dimension; calculating the nuclear tensor, and updating a result through dynamic learning until an algorithm convergence result reaches the best; repeating the processes for representing all videos as nuclear tensors same in size, namely, zooming video sequences to be same in dimension; and realizing tensor decomposition under a non-equilateral condition. According to the method, the difficulty in gesture identification is lowered, the accuracy of gesture identification is improved, good conditions are provided for subsequent video sequence classification, and the accuracy of video sequence classification can be greatly improved.

Description

technical field [0001] The present invention relates to a tensor decomposition method. In particular, it concerns a tensor decomposition method for gesture recognition in unequal-length videos. Background technique [0002] With the dramatic increase in the number of available videos, content-based video analysis has been widely applied to video retrieval, action recognition, video summarization, etc. Hands and fingers have high dexterity compared to other parts of the human body, so it is one of the most efficient and versatile ways to interact with the outside world. As an important part of the semantic analysis of human actions, gesture recognition has been widely used. For example, in a hospital visit, a gesture recognition system can allow doctors to manipulate digital images through gestures. [0003] The goal of gesture recognition is to correctly classify gesture video sequences. Although there have been some works on gesture recognition, there are still many cha...

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): G06K9/00
CPCG06V40/28
Inventor 苏育挺王慧晶井佩光张静
Owner TIANJIN 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