Human Activity Detection from RGBD Images

Abstract

Being able to detect and recognize human activities is important for making personal assistant robots useful in performing assistive tasks. The challenge is to de-velop a system that is low-cost, reliable in unstructured home settings, and also straightforward to use. In this paper, we use a RGBD sensor (Microsoft Kinect) as the input sensor, and present learning algorithms to in-fer the activities. Our algorithm is based on a hierar-chical maximum entropy Markov model (MEMM). It considers a person’s activity as composed of a set of sub-activities, and infers the two-layered graph struc-ture using a dynamic programming approach. We test our algorithm on detecting and recognizing twelve dif-ferent activities performed by four people in different environments, such as a kitchen, a living room, an of-fice, etc., and achieve an average performance of 84.3% when the person was seen before in the training set (and 64.2 % when the person was not seen before).