Abstract: Indoor pedestrian positioning serves as a crucial foundation for location-based services, with geomagnetic signals being continuously perceived, making them a focal point in indoor pedestrian positioning research. Addressing the challenges of significant cumulative errors and low positioning accuracy in current particle filter fusion positioning, this paper proposes an indoor pedestrian positioning method: variable-length geomagnetic sequence assisted PSO-PF. Building upon traditional particle filter algorithms, this method integrates particle swarm optimization for optimal position to enhance real-time positioning accuracy. Subsequently, a DTW-A^* algorithm is established to correct cumulative errors over time for variable-length geomagnetic sequences, address the cumulative error problem associated with particle filter-based positioning methods. Experimental comparisons with existing mainstream positioning methods demonstrate that the proposed method achieves an average error of 0.90 m in indoor pedestrian positioning. The average error is reduced by 73.1%, 68.0%, and 63.8% compared to PDR, MaLoc, and Magicol methods, respectively. Notably, the proposed method achieves a 1.43 m positioning accuracy at 90%, showing a relative improvement of 75.1%, 68.4%, and 67.7% compared to PDR, MaLoc, and Magicol methods, respectively. Furthermore, experimental results on different models of smart phones indicate that the proposed research method is not only applicable,but also stable, offering potential support for indoor positioning across various devices.

Key words: geomagnetic indoor pedestrian positioning, PSO-PF, geomagnetic sequences, pedestrian trajectory estimation