An efficient method of human behavior recognition in smart environments
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.
vision-based behavior recognition gradient orientation
Chun-Hua Hu Song-Lin Wo
School of Electrical and Information Engineering, Jiangsu Teacher University of Technology Changzhou, Jiangsu Province, China
国际会议
太原
英文
690-693
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）