kPose: A New Representation For Action Recognition

Human action recognition is an important problem in computer vision. Most existing techniques use all the video frames for action representation, which leads to high computational cost. Different from these techniques, we present a novel action recognition approach by describing the action with a few frames of representative poses, namely kPose. Firstly, a set of pose templates corresponding to different pose classes are learned based on a newly proposed Pose-Weighted Distribution Model (PWDM). Then, a local set of kPoses describing an action are extracted by clustering the poses belonging to the action. Thirdly, a further kPose selection is carried out to remove the redundant poses among the different local sets, which leads to a global set of kPoses with the least redundancy. Finally, a sequence of kPoses is obtained to describe the action by searching the nearest kPose in the global set. And the proposed action classification is carried out by comparing the obtained pose sequence with each local set of kPose. The experimental results validate the proposed method by remarkable recognition accuracy.