Key Points of Human Body Location Based on Single Depth Map

Abstract

This paper presents a method of using single depth map to locate the key points of frontal human body. Human motion capture is the premise of motion analysis and understanding, and it has widely application prospects. There are many problems on former way to capture the state of human motion. For example, it can’t initialize automatically, it can not recover from tracking failure, it can not solve the problem caused by occlusion, or there are many constraints on participant, and so on. This article uses Kinect, which from Microsoft, to get depth maps, and use a single map as input to locate the key points of human body. First, depth map can reflect the distance, so background segmentation can be done easily by the characteristic. Then, extract the skeleton of the body’s silhouette. Finally, using the inherent connectivity features of human body, the key points of the body can be determined on the skeleton. Locating the key points from single depth map solve the problem of automatic initialization and recovery directly. The depth map can reflect distance on grayscale, which makes it easy to split the body region from the background. In addition, depth map contains some useful information can be used to solve the problem of occlusion. Using depth map can remove some constraints on the human body, as well as to reduce the influence of clothing and surround lighting, and so on. The experiment shows that this method is very accurate in locating the key points of frontal stand human body, and can solve some problems of occlusion. It is ideal used in a motion tracking system for automatic initialization and self-recovery when tracking failed