Human Body Movement Identification

Abstract

Abstract

Human Body Movement Identification is the recognition technique of moving human behavior, it detects and traces the moving human body movements. A 3D human body is expressed by a multi-joint model and describe the posture by a set of joint angles. It is necessary to recognize the human body movements for computer-human interaction. It is useful in many scientific and security fields. It can be used in camera surveillance, sports as well as military applications. In this system, we propose a method to estimate human movements using Deep Learning and Machine Learning features with Pretrained Data set. Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. The method does not depend on clothes and orientation under noisy conditions so that the human movement can be estimated stably.