CAMP: A Context-Aware, Multimodal, and Privacy-Preserving Pedestrian Trajectory Prediction Framework
Journal of Imaging · 02.05.2026 · 12 (5) · 197
DOI: 10.3390/jimaging12050197 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 02.05.2026. Verfasst von Bin Yue und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Computer Science, Shaanxi Normal University, Xi'an 710119, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China (NSFC).
Abstract (Originalsprache)
Pedestrian trajectory prediction is vital for crowd analysis and human–-robot interaction. Recent deep models enhance accuracy by modeling social interactions and scene context, but they often remain opaque and rarely address privacy risks associated with learning individualized motion patterns. We propose CAMP, a Context-Aware, Multimodal, and Privacy-preserving pedestrian trajectory prediction framework designed around a role-aligned multimodal architecture, in which trajectory representations, dynamic scene cues, and explicit spatial interaction constraints are modeled through complementary branches. In CAMP, the trajectory encoder separates shared motion regularities from individualized motion tendencies, the optical-flow encoder captures motion-centric transient scene dynamics, and the potential-field encoder provides an interpretable spatial cost prior for obstacle avoidance and social interaction modeling. A Transformer-based decoder fuses these modalities to predict future trajectory distributions. To reduce the exposure of personalized motion patterns, we apply targeted DP-SGD only to the individual branch during the private fine-tuning stage, while treating the remaining frozen components as post-processing under the stated threat model. Experiments on the ETH/UCY benchmark show that CAMP achieves competitive ADE/FDE performance under the reported setting, while its private variant DP-CAMP maintains a reasonable utility–privacy trade-off across several reported privacy budgets.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Artificial Intelligence and Computer Science, Shaanxi Normal University, Xi'an 710119, China.
Förderung
- National Natural Science Foundation of China (NSFC)
Zitieren
APA
Yue, B., Li, S., & Liu, A. (2026). CAMP: A Context-Aware, Multimodal, and Privacy-Preserving Pedestrian Trajectory Prediction Framework. Journal of Imaging, 12(5), 197. https://doi.org/10.3390/jimaging12050197
Vancouver
Yue B, Li S, Liu A. CAMP: A Context-Aware, Multimodal, and Privacy-Preserving Pedestrian Trajectory Prediction Framework. Journal of Imaging. 2026;12(5):197. doi:10.3390/jimaging12050197
BibTeX
@article{Yue2026,
author = {Yue, Bin and Li, Shuyu and Liu, Anyu},
title = {CAMP: A Context-Aware, Multimodal, and Privacy-Preserving Pedestrian Trajectory Prediction Framework},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {5},
pages = {197},
doi = {10.3390/jimaging12050197}
}
EUVIMED