Search results

The pedestrian dead reckoning (PDR) based on smartphones has been widely applied in continuous indoor positioning. However, when the position of the mobile phone and the walking patterns of the pedestrian are mixed, traditional PDR tends to become confused and thus degrade performance. To address this issue, this paper aims to propose an improved PDR scheme by focusing on gait pattern recognition and the impact of short-period but negative transitions on tracking.

The overall solution uses the inertial sensor integrated within the phone for positioning. A binary classifier-based change point detection algorithm is used to identify the transition points in pedestrian gait. Additionally, to enhance the accuracy of gait recognition, this paper presents a combined CNN-attention-based bi-directional long short-term memory(ABiLSTM) model, integrating convolutional neural networks (CNN), bi-directional long short-term memory (Bi-LSTM) and an attention mechanism, to recognize the current gait pattern. The outcomes of this gait pattern recognition are then applied to PDR. Based on distinct gait patterns, corresponding PDR strategies are devised to enable continuous tracking and positioning of pedestrians.

Through experimental verification, the CNN-ABiLSTM model achieves a gait recognition accuracy of 99.52% on the self-constructed data set. The pedestrian navigation estimation method proposed in this paper, which is based on gait recognition assistance, demonstrates a 32.56% improvement in accuracy over traditional positioning algorithms in multi-gait scenarios.

The improved PDR scheme algorithm significantly enhances the robustness and smoothness of pedestrian tracking, particularly during multiple gait transitions. This, in turn, provides strong support for the utilization of low-cost inertial sensors integrated within mobile phones for indoor positioning applications.