Pedestrian dead reckoning (PDR) can be used for continuous position estimation when satellite or other radio signals are not\navailable, and the accuracy of the stride length measurement is important. Current stride length estimation algorithms, including\nlinear and nonlinear models, consider a few variable factors, and some rely on high precision and high cost equipment. This\npaper puts forward a stride length estimation algorithm based on a back propagation artificial neural network (BP-ANN), using\na consumer-grade inertial measurement unit (IMU); it then discusses various factors in the algorithm. The experimental results\nindicate that the error of the proposed algorithm in estimating the stride length is approximately 2%, which is smaller than that of\nthe frequency and nonlinear models. Compared with the latter two models, the proposed algorithm does not need to determine\nindividual parameters in advance if the trained neural net is effective. It can, thus, be concluded that this algorithm shows superior\nperformance in estimating pedestrian stride length.
Loading....