With the rapid development of wireless sensing, trajectory-tracking methods based on Wi-Fi channel state information (CSI) have broad applicability in intelligent security systems, indoor navigation, and related scenarios owing to their low cost, contactless operation, and ease of deployment. Nevertheless, the high variability and noise of CSI limit the robustness and accuracy of existing methods, particularly in complex environments with dynamic pedestrian behavior. This paper proposes an indoor pedestrian trajectory-tracking framework that integrates deep learning, diffusion-based data augmentation, and particle filtering. First, we collect CSI in real environments and employ a diffusion model to augment the dataset, thereby improving the model's generalization. Next, a CNN-LSTM architecture extracts spatiotemporal features from CSI and learns a mapping from CSI to pedestrian positions. Finally, particle filtering is applied to smooth and reconstruct continuous position states over time. The proposed system achieves high-accuracy trajectory reconstruction in dynamic environments, with localization errors of approximately 0.5 m. It generalizes across diverse settings and demonstrates strong practical value and scalability.

Network Kernel Density Visualization (NKDV) has often been used in a wide range of applications, e.g., criminology, transportation science, and urban planning. However, NKDV is computationally expensive, which cannot be scalable to large-scale datasets and high resolution sizes. Although a recent work, called aggregate distance augmentation (ADA), has been developed for improving the efficiency to generate NKDV, this method is still slow and does not take the resolution size into account for optimizing the efficiency. In this paper, we develop a new solution, called LION, which can reduce the worst-case time complexity for generating high-resolution NKDV, without increasing the space complexity. Experiment results on four large-scale location datasets verify that LION can achieve 2.86x to 35.36x speedup compared with the state-of-the-art ADA method.