ISPRS International Journal of Geo-Information, Volume 14, Issue 10
2025 October - 41 articles
Cover Story: Forecasting pedestrian congestion in urban back streets is challenging due to “shadow areas” where CCTV coverage is absent and trajectory data cannot be directly collected. This study proposes the Peak-Graph Temporal Fusion Transformer (PGTFT), a lightweight deep learning model designed to predict pedestrian congestion in these data-sparse areas. By integrating a non-parametric attention GCN and a hybrid adjacency matrix combining hop-based and distribution-based similarities, the model captures both structural and functional relationships among road segments. The inclusion of a mini Variable Selection Network and a Peak-aware GRN enhances efficiency and sensitivity to irregular congestion peaks, demonstrating robust and accurate reconstruction of pedestrian flow in shadow areas. View this paper - Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.