作者: I-Cheng Chang , Chung-Lin Huang , None
DOI: 10.1016/S0262-8856(00)00046-9
关键词:
摘要: Abstract In this paper, we propose a model-based method to analyze the human walking motion. This system consists of three phases: preprocessing phase, model construction and motion analysis phase. experimental results, show that our not only analyzes characteristics body, but also recognizes type input image sequences. Finally, synthesized sequences are illustrated for verification. The major contributions research are: (1) developing skeleton-based motion; (2) using Hidden Markov Model (HMM) posture patterns describe type.