Pose primitive based human action recognition in videos or still images

This paper presents a method for recognizing human actions based on pose primitives. In learning mode, the parameters representing poses and activities are estimated from videos. In run mode, the method can be used both for videos or still images. For recognizing pose primitives, we extend a Histogram of Oriented Gradient (HOG) based descriptor to better cope with articulated poses and cluttered background. Action classes are represented by histograms of poses primitives. For sequences, we incorporate the local temporal context by means of n-gram expressions. Action recognition is based on a simple histogram comparison. Unlike the mainstream video surveillance approaches, the proposed method does not rely on background subtraction or dynamic features and thus allows for action recognition in still images.

1. Introduction

Human action recognition aims at automatically telling the activity of a person, i.e. to identify if someone is walking, dancing, or performing other types of activities. It is a crucial prerequisite for a number of applications, including surveillance, content-based image retrieval, or human-robot interaction. The task is challenging due to changes in the appearance of persons, articulation in poses, changing backgrounds, and camera movements.