作者: Bin Zhang , Tomoaki Nakamura , Rena Ushiogi , Takayuki Nagai , Kasumi Abe
关键词:
摘要: Developing a childcare assisting system is highly necessary due to the lack of nursery teachers, and it will make an important progress on effective utilization teacher resources. In this paper, we proposed simultaneous children recognition tracking by using Kinect sensors for provide information teachers. Each recognized integrating his/her personal color, face motion. The problem modeled as finding MAP solution posterior probability, solved Markov Chain Monte Carlo (MCMC) particle filter. Our can recognize robustly track each child during class activities. Trajectories, motion ranges relative distances be provided teachers assist their work. effectiveness our proved through continuous monitoring in school.