Efficient Body Motion Quantification and Similarity Evaluation Using 3-D Joints Skeleton Coordinates

Evaluating whole-body motion is challenging because of the articulated nature skeleton structure. Each joint moves in an unpredictable way with uncountable possibilities movements direction under influence one or many its parent joints. This paper presents a method for human quantification via three-dimensional (3-D) body joints coordinates. We calculate set metrics that movement considering without requiring prior knowledge parameters. Only raw coordinates data sequence are needed to automatically estimate transformation matrix between frames. also consider angles limbs as fundamental factor follow directions. classify global and local motion. The represents according fixed joint, first joint. In order evaluate performance proposed method, we propose comparison algorithm two skeletons motions based on quantified metrics. measured comparative similarity 3-D Microsoft Kinect V2 UTD-MHAD dataset. User studies were conducted different factors. Various results comparisons have shown our effectively quantifies evaluates similarity.