I. Introduction
Human action recognition [1]–[5] is an active yet challenging research area that has been explored in many applications including healthcare, smart surveillance, and security. RGB sensors and depth sensors (e.g., Microsoft Kinect sensors) have been used to improve human action recognition performance by exploiting rich, captured information such as depth and 3D location. Compared to RGB data, depth data can adapt to changes in lighting conditions through the use of infrared radiation. Xiao et al. [6] and Ji et al. [7] proposed an effective method to recognize human actions from depth map sequences. However, due to redundancy in depth maps, this huge amount of data increases computational complexity making them impractical for real-world use.