Wireless fingerprinting localization (FL) systems identify locations by building radio fingerprint maps, aiming to provide satisfactory location solutions for the complex environment. However, the radio map is easy to change, and the cost of building a new one is high. One research focus is to transfer knowledge from the old radio maps to a new one. Feature-based transfer learning methods help by mapping the source fingerprint and the target fingerprint to a common hidden domain, then minimize the maximum mean difference (MMD) distance between the empirical distributions in the latent domain. In this paper, the optimal transport (OT)-based transfer learning is adopted to directly map the fingerprint from the source domain to the target domain by minimizing the Wasserstein distance so that the data distribution of the two domains can be better matched and the positioning performance in the target domain is improved. Two channel-models are used to simulate the transfer scenarios, and the public measured data test further verifies that the transfer learning based on OT has better accuracy and performance when the radio map changes in FL, indicating the importance of the method in this field.
Accurate pedestrian localization in global navigation satellite system (GNSS)-denied environments remains a critical challenge. This paper proposes an IMU-based fusion method to address the limitations of current pedestrian dead reckoning (PDR) systems in gait detection and heading drift. The method integrates an Adaptive Time Thresholding algorithm based on Estimated Gait Period (ATT-EGP), a dynamic gyroscope error model with zero-bias compensation for drift reduction and a robust heuristic drift elimination (HDE) algorithm for heading correction. The ATT-EGP algorithm dynamically adjusts thresholds based on real-time gait period estimation, demonstrating consistent performance across three participants. Experimental results show gait detection errors in the range of 0.8%-1.4% for running, 0.6%-2.0% for normal walking, and 0.2%-1.2% for fast walking, achieving improvements of 51.8%-98.3% compared to conventional dual-threshold methods. Combined with the robust HDE algorithm, the system significantly reduces endpoint errors in pedestrian trajectories. Experimental results demonstrate average endpoint error reductions of 54.4% in walking mode, 63.3% in running mode, and 93.1% in multi-motion mode compared to traditional peak detection methods.
Pedestrian trajectory prediction from a vehicle-mounted perspective is essential for autonomous driving in complex urban environments yet remains challenging due to ego-motion jitter, frequent occlusions, and scene variability. Existing approaches, largely developed for static surveillance views, struggle to cope with continuously shifting viewpoints. To address these issues, we propose V-PTP-IC, an end-to-end framework that stabilizes motion, models inter-agent interactions, and fuses multi-modal cues for trajectory prediction. The system integrates Simple Online and Realtime Tracking (SORT)-based tracklet augmentation, Scale-Invariant Feature Transform (SIFT)-assisted ego-motion compensation, graph-based interaction reasoning, and multi-head attention fusion, followed by Long Short-Term Memory (LSTM) decoding. Experiments on the JAAD and PIE datasets demonstrate that V-PTP-IC substantially outperforms existing baselines, reducing ADE by 27.23% and 25.73% and FDE by 33.88% and 32.85%, respectively. This advances dynamic scene understanding for safer autonomous systems.