Study on Recent Approaches for Human Action Recognition in Real Time

Abstract

The important area in computer vision is human understanding and recognizing actions. The main aim of action recognition is an automatic analysis of various actions from video data. Major video analysis system includes action detection and classification, action tracking, recognizing actions and behavior understanding. Even though, traditional methods have achieved greater success on several human actions. But, still it is a challenging problem to recognize human action. The challenge is to recognize human actions with more accuracy and efficiency in recognition time. The action recognition application includes CCTV, video indexing, patient monitoring systems and HCI systems. In this paper, we focus our attention to various modern approaches to human action recognition in real time. Keywords-Sparse tree, Ratio histogram, Code book, Hidden Markov model, Tree based codebook, bag-of-features.