An efficient method of human behavior recognition in smart environments

Abstract

The task of reliably detecting and recognizing the action of a specific person for smart space is challenging. In this paper, an efficient vision-based method of human behavior recognition in smart environments is proposed, which utilizes the template match method by edge gradient orientation method for extracting the critical points of human and using the Hidden Markov Model (HMM) to construct the behavior recognition classifer. Various experiments are carried out and the results demonstrate the robustness and reliability in human behavior recognition.