Cross-Modal Vehicle Detection, Tracking, and Counting from Hyperspectral to RGB Imagery Using Spatial–Spectral Fusion and Knowledge Distillation
Sensors · 19.11.2026 · 26 (22) · 7304
DOI: 10.3390/s26227304 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 19.11.2026. Verfasst von Viktoria Meskova und 4 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Accurate vehicle detection, tracking, and counting are central to intelligent transportation systems. Most existing approaches rely on RGB imagery and often suffer from performance degradation when vehicles are partially blocked, lighting conditions change, backgrounds are complex, or traffic is heavy. Hyperspectral imaging provides additional spectral information that can help distinguish vehicles more effectively, although its use in end-to-end traffic analysis and its transferability to conventional RGB imagery remain relatively unexplored. In this study, we propose a unified vehicle-analysis framework combining Edge-Guided Dimensionality Reduction (EGDR), a Spatial Context Enhancement Module (SCEM), and teacher-guided pseudo-label knowledge distillation. EGDR preserves spectral, edge, and multi-scale spatial information in a compact three-channel representation, while SCEM enhances contextual feature extraction. An EGDR+SCEM YOLOv11m detector is used as a teacher, from which a lightweight YOLOv11s student is trained through knowledge distillation. The student detector is then combined with tracking and trajectory-based counting to form a complete vehicle-analysis pipeline. On the HSI-Drive dataset, the distilled student improved mAP50 from 0.740 ± 0.020 to 0.780 ± 0.016 and mAP50:95 from 0.508 ± 0.018 to 0.532 ± 0.006 across six training seeds while retaining the same 9.41M-parameter, approximately 21-GFLOP student architecture. We further evaluated direct cross-modal generalization by testing the hyperspectral-trained model on RGB UA-DETRAC video sequences without RGB-domain fine-tuning or adaptation. Distillation improved RGB mAP50:95 from 0.5377 to 0.5809 and increased trajectory-based counting accuracy from 84.72% to 87.50%, while reducing average counting error from 15.28% to 12.50%. Thus, supervision derived from hyperspectral-trained vehicle representations can improve lightweight detector generalization to RGB traffic imagery and support detection, tracking, and counting across sensing modalities.
Förderung
- National Science Foundation
Zitieren
APA
Meskova, V., Soni, J., Rishe, N., Upadhyay, H., & Adjouadi, M. (2026). Cross-Modal Vehicle Detection, Tracking, and Counting from Hyperspectral to RGB Imagery Using Spatial–Spectral Fusion and Knowledge Distillation. Sensors, 26(22), 7304. https://doi.org/10.3390/s26227304
Vancouver
Meskova V, Soni J, Rishe N, Upadhyay H, Adjouadi M. Cross-Modal Vehicle Detection, Tracking, and Counting from Hyperspectral to RGB Imagery Using Spatial–Spectral Fusion and Knowledge Distillation. Sensors. 2026;26(22):7304. doi:10.3390/s26227304
BibTeX
@article{Meskova2026,
author = {Meskova, Viktoria and Soni, Jayesh and Rishe, Naphtali and Upadhyay, Himanshu and Adjouadi, Malek},
title = {Cross-Modal Vehicle Detection, Tracking, and Counting from Hyperspectral to RGB Imagery Using Spatial–Spectral Fusion and Knowledge Distillation},
journal = {Sensors},
year = {2026},
volume = {26},
number = {22},
pages = {7304},
doi = {10.3390/s26227304}
}
EUVIMED