Intelligent object localization system based on activity theory in home environment

摘要

Object localization is the premise and key problem of object-operating. Aiming at the low efficiency of object localization and management, an Activity Theory based intelligent object management scheme is presented in the paper, which can arrive at the state of object through people's activity including movement trajectory and behavior. The RFID tags stuck on the object can bind the information space with physical space, thus the information space can automatically sense the changes in physical space. Object detection, body localization and action recognition are realized using real-time data provided by RFID, distributed vision and Inertial Navigation Module, combined with database of the intelligent space. Object localization oriented Dynamic Bayesian Network is built to automatically sense and update the state of object through activity analyses of people. The research can improve the precision and efficiency of object localization to a large extent, realize intelligent object localization, and has an important significance for service robot to entering home environment.