Recognition and classification of human activity from RGB-D videos

Human activity recognition has many applications in computer vision, including personal assistive robotics and smart homes/environments. Due to the large temporal and spatial variations in actions performed by humans, human action recognition has been a long-standing challenge. This paper presents a method that recognizes certain human activities based on a motion descriptor that uses 3D human skeleton data. A motion descriptor (SHOJD) is defined using the 3D distance between the most frequent key poses that occur throughout the action that is intended to be recognized. SHOJD features are then fed into an artificial neural network for classification. Experimental results indicate that the SHOJD based human action recognition system is robust with high recognition rate.