Motion recognition method based on sparse coding tensor decomposition

Abstract

The invention provides a motion recognition method based on sparse coding tensor decomposition. An original video sequence is expressed as a three-order video sequence tensor A belongs to R<I<1>xI<2>xT>, wherein T refers to the length of the video sequence, and I<1>xI<2> refers to the size of the video frame; Tucker decomposition is performed on the three-order video sequence tensor A belongs to R<I<1>xI<2>xT> so that a nuclear tensor of which the spatial domain dimension is reduced is acquired; the video sequence tensor is zoomed to the same scale; and the result is updated by dynamically learning the process until the algorithm convergence result achieves the optimum. According to the motion recognition method based on sparse coding tensor decomposition, the video sequence can be processed into the unified length-the sparse coding tensor decomposition technology. The frames of the most information are adaptively selected from a tensor decomposition framework in the process to construct a new video sequence having the unified video sequence length. According to the method, the difficulty of gesture recognition can be reduced and the accuracy of gesture recognition can be enhanced so that the great conditions can be provided for subsequent video sequence classification, and the accuracy of video sequence classification can be enhanced.

Description

technical field [0001] The invention relates to an action recognition method. In particular, it relates to an action recognition method based on tensor decomposition of sparse codes, Background technique [0002] With the dramatic increase in the number of videos available, content-based video analysis has attracted great attention in areas such as video retrieval, action recognition, and video summarization. Due to the high dexterity of the hands and fingers, gestures are the most efficient and versatile way of interacting with the outside world compared to other human body parts. 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 purpose of gesture recognition can be seen as classifying video sequences. In recent years, there have been some works on gesture recognition, but de...

AI Technical Summary

Problems solved by technology

However, in these methods of classifying videos based on tensor decomposition, there is a basic but neglected problem: all video sequences need to have a uniform video sequence length in the time dimension

However, this method of operation will lead to the following shortcomings: 1) The newly constructed video sequence cannot fully characterize the gesture; 2) It cannot rely on the speed change in the gesture to automatically capture the key frames in the video sequence

Images