A Novel Probabilistic Based Image Segmentation Model for Realtime Human Activity Detection

摘要

Automatic human activity detection is one of the difficult tasks in image segmentation application due tovariations in size, type, shape and location of objects. In the traditional probabilistic graphicalsegmentation models, intra and inter region segments may affect the overall segmentation accuracy. Also,both directed and undirected graphical models such as Markov model, conditional random field havelimitations towards the human activity prediction and heterogeneous relationships. In this paper, we havestudied and proposed a natural solution for automatic human activity segmentation using the enhancedprobabilistic chain graphical model. This system has three main phases, namely activity pre-processing,iterative threshold based image enhancement and chain graph segmentation algorithm. Experimentalresults show that proposed system efficiently detects the human activities at different levels of the actiondatasets.