Towards accurate and robust map-aid indoor human tracking

One critical issue in indoor human tracking is the design of map-aid algorithms that exploit indoor layout information. Most of current works adopt similar map-aid calibration techniques that eliminate invalid particles, which means particles propagating in inhumane manner. However, we find that these techniques have two serious problems in common, which we name acute sample impoverishment and observation noise vulnerability. To address these problems, we propose an Immune Location Factor Particle Filter (ILFPF) in this paper. The ILFPF overcomes the acute sample impoverishment problem through Clonal Selection Algorithm based re-sampling, which is robust against observation noise due to the introduction of Location Factor. Simulation results show that our proposed algorithm has an accuracy 36% higher than that of standard particle filter.