Video human action reorganization method based on sparse subspace clustering

Abstract

The invention belongs to computer visual pattern recognition and a video picture processing method. The computer visual pattern recognition and the video picture processing method comprise the steps that establishing a three-dimensional space-time sub-frame cube in a video human action reorganization model, establishing a human action characteristic space, conducting the clustering processing, updating labels, extracting the three-dimensional space-time sub-frame cube in the video human action reorganization model and the human action reorganization from monitoring video, extracting human action characteristic, confirming category of human sub-action in each video and classifying and merging on videos with sub-category labels. According to the computer visual pattern recognition and the video picture processing method, the highest identification accuracy is improved by 16.5% compared with the current international Hollywood2 human action database. Thus, the video human action reorganization method has the advantages that human action characteristic with higher distinguishing ability, adaptability, universality and invariance property can be extracted automatically, the overfitting phenomenon and the gradient diffusion problem in the neural network are lowered, and the accuracy of human action reorganization in a complex environment is improved effectively; the computer visual pattern recognition and the video picture processing method can be applied to the on-site video surveillance and video content retrieval widely.

Description

technical field [0001] The invention belongs to computer vision pattern recognition and video image processing methods, in particular to a neural network based on deep learning that adopts sparse subspace (SSC) clustering and subdivision and splits a large number of layers into several layers Fewer shallower approaches to video action recognition based on deep learning neural networks. Background technique [0002] Human behavior recognition based on video is a hot issue in the field of computer vision in recent years. As a typical video understanding problem, human behavior patterns can be identified and determined by analyzing the characteristics of human motion in video image sequences. More specifically, it extracts feature information that can describe behavior from video image sequences, uses machine learning and other technologies to understand it, and uses classifiers to classify to achieve the purpose of recognizing human behavior. [0003] With the development of ...

AI Technical Summary

Problems solved by technology

Although this method has strong anti-interference ability to the specific direction of the human body, bone size, and spatial position, and has a certain degree of generalization ability, it can be applied to human behavior recognition in a more ideal environment, but it needs to use 3D technology with high cost. In addition, the algorithm of this method is relatively complex, and the effect of human behavior recognition in more complex scenes is still not ideal

Images