Multisensor data fusion for joint people tracking and identification with a service robot

摘要: Tracking and recognizing people are essential skills modern service robots have to be provided with. The two tasks generally performed independently, using ad-hoc solutions that first estimate the location of humans then proceed with their identification. solution presented in this paper, instead, is a general framework for tracking simultaneously mobile robot, where estimates human identity fused probabilistic techniques. Our approach takes inspiration from recent implementations joint classification, considered targets mainly vehicles aircrafts military civilian applications. We illustrate how can robustly tracked recognized robot an improved histogram-based detection multisensor data fusion. Some experiments real challenging scenarios show good performance our solution.