30 January 2024 in IEEE Sensors Journal
In an intelligent information society, indoor pedestrian navigation systems based on inertial sensors are becoming increasingly important due to advantages of autonomy and continuity in positioning. However, these systems cannot estimate pedestrian altitude because of the divergence of inertial altitude channels and the complexity of pedestrian movement patterns. To address this challenge, this paper proposes an indoor pedestrian altitude estimation method utilizing the inertial measurement unit (IMU) sensor installed on the pedestrian’s foot. Specifically, the method calculates the height difference of steps with the inertial navigation system (INS), extended Kalman filter (EKF), and zero-velocity update (ZUPT), named the IEZ framework. Then, a convolutional neural networks-support vector machine (CNN-SVM) model is developed to accurately identify complex pedestrian motion patterns including horizontal walking, running, walking stairs, standing, and taking elevators and escalators. Next, the height difference is adaptively corrected according to the motion modes. For horizontal walking and standing, the height difference based on the IEZ framework is revised and remains unchanged; for walking or running stairs, the pedestrian altitude is determined by the stair step model. In the case of taking elevators or escalators, the vertical displacement is obtained by integrating the barometric height measured as EKF observations with the double integral value of the vertical acceleration. Experimental results show that the CNN-SVM model achieves a classification accuracy of 98.8%, and a positioning error for pedestrian altitude estimation of less than 0.6 m with an indoor walking distance of approximately 500 m.
15 January 2024 in IEEE Sensors Journal
Due to the low-quality sensors of consumer-grade devices, such as smartphones, traditional point-based visual-inertial SLAM (Simultaneous Localization and Mapping) techniques applied to smartphones commonly suffer from low localization accuracy and potential tracking divergence. Incorporating more measurements can enhance localization performance and robustness, but the additional computational consumption may not satisfy the real-time requirements in mobile location-based services, such as pedestrian positioning. For mobile SLAM applications focused on pedestrians in human-made environments, this paper proposes PS-VINS, a real-time visual-inertial SLAM system using smartphone sensors, exploiting additional motion constraints from pedestrian gait and geometric constraints from structural line features. To enhance the pose estimation accuracy of back-end optimization, we incorporate motion measurement models of step velocity and length by utilizing extracted pedestrian gait information. Additionally, we establish vanishing point (VP) and structural camera rotation measurement models based on structural line features. To ensure high efficiency, we present efficient methods for gait information extraction and VP estimation. PS-VINS can further integrate GNSS(Global Navigation Satellite System) output from smartphones to achieve global positioning in open outdoor environments. The field test results, including both outdoor and indoor environments, demonstrate that PS-VINS addresses the issue of drift error due to the low-quality smartphone sensors, achieving improved localization accuracy and efficiency compared to the state-of-the-art SLAM techniques.