Movement path estimation for multiple humans in a room using binary infrared sensors

To create a context-aware environment for humans in a room, their locations and movement paths must be considered. In this paper, we propose an algorithm that estimates human movement paths only using the binary sensed data obtained by infrared (IR) sensors attached to the ceiling. Our algorithm can estimate multiple human movement paths without knowing the number of humans in the room beforehand. By repeating estimations of human positions and links from the previous human positions to the estimated ones at each time period, human movement paths can be estimated. Simulation-based evaluation results show that our algorithm can dynamically trace human movement paths within 0.6 m error on average.