Video motion characteristic extracting method based on local sparse constraint non-negative matrix factorization

Abstract

The invention discloses a video motion characteristic extracting method based on local sparse constraint non-negative matrix factorization. The video motion characteristic extracting method mainly solves the problems that static background interference and flash points of a video cannot be filtrated, the convergence rate is low, and the factorization error is over-serious in the prior art. The video motion characteristic extracting method comprises the steps of: firstly converting a video into a video frame group by taking a target frame as the center, and converting the video frame group into a non-negative matrix; next, factorizing the non-negative matrix by a local sparse constraint non-negative matrix factorization method, carrying out sparse constraint on part of base matrix column vectors, and calculating a motion vector of the target frame through weighted summarization of the part of the base matrix column vectors undergoing sparse constraint and the corresponding coefficient matrixes; and finally converting the motion vector of the target frame into the motion characteristic of the target frame. The video motion characteristic extracting method disclosed by the invention is applicable to target tracking and video monitoring, and can be used for extracting the video motion characteristic quickly, accurately and effectively.

Description

technical field [0001] The invention belongs to the technical field of image processing and relates to video motion feature extraction, which can be used in target tracking and video monitoring to quickly, accurately and effectively extract video motion features and clearly display motion tracks. Background technique [0002] Video motion feature is one of the important features of video, which is widely used in object tracking and video surveillance. At present, great progress has been made in video motion feature extraction, but how to accurately detect moving objects in video streams is still a challenging problem. Some algorithms need to manually adjust parameters or set some assumptions. One of the widely used methods is based on the background difference method, which is a pixel-based motion feature extraction method. First, it needs to accurately estimate the background model of the video, and then use The difference between the current frame and the background is us...

AI Technical Summary

Problems solved by technology

A non-negative matrix factorization method that can precisely control the sparsity is proposed, which can realize the precise control of the sparsity of the basis matrix and the coefficient matrix at the same time with nonlinear projection, but the sparsity constraint is added to all basis vectors, and when a higher When sparsity is constrained, the description of the data is not enough, the decomposition error is too large, and the convergence speed is slow

Images