Human action segmentation and recognition via motion and shape analysis

In this paper, we present an automated video analysis system which addresses segmentation and detection of human actions in an indoor environment, such as a gym. The system aims at segmenting different movements from the input video and recognizing the action types simultaneously. Two action segmentation techniques, namely color intensity based and motion based, are proposed. Both methods can efficiently segment periodic human movements into temporal cycles. We also apply a novel approach for human action recognition by describing human actions using motion and shape features. The descriptor contains both the local shape and its spatial layout information, therefore is more effective for action modeling and is suitable for detecting and recognizing a variety of actions. Experimental results show that the proposed action segmentation and detection algorithms are highly effective.

► We propose two temporal action segmentation methods based on color intensity change and motion analysis. ► PCOG is used as a global descriptor on motion history images for action representation and recognition. ► The system can automatically segment, count and recognize human actions in an indoor environment.