From Detection to Functional Analysis: Evaluating Vehicle Detection Models in High-Resolution Earth Observation Imagery
Remote Sensing · 03.07.2026 · 18 (13) · 2166
DOI: 10.3390/rs18132166 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 03.07.2026. Verfasst von Damian Wierzbicki und 3 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Military University of Technology, Faculty of Civil Engineering and Geodesy.
Abstract (Originalsprache)
The rapid development of deep learning methods has significantly improved the effectiveness of object detection in Earth Observation (EO) imagery. However, standard metrics such as Mean Average Precision (mAP) do not fully reflect their utility in operational analyses. This paper proposes a multi-stage methodology for evaluating vehicle detection models, combining classical evaluation with functional analysis encompassing object counting, density estimation, and occupancy index. The research was conducted on high-resolution imagery (WorldView, Pleiades) and the xView dataset, evaluating five YOLO variants alongside transformer-based and two-stage detectors under three training strategies, including fine-tuning. The results show that models achieving high mAP values (up to 0.952) can simultaneously produce significant errors in object count estimation. Models trained exclusively on xView exhibit a substantial performance drop (mAP@0.50 ≈ 0.45) under domain shift conditions. The best results were obtained using a fusion-based approach combining YOLOv9 and YOLOv12, which reduced the mean relative error to 0.14 and the counting error to 13 objects, maintaining a low density error (0.0023). Functional validation across 20 parking areas confirmed the stability of the proposed approach. The findings confirm that functional analysis constitutes a critical complement to classical evaluation in remote sensing applications.
Förderung
- Military University of Technology, Faculty of Civil Engineering and Geodesy
Zitieren
APA
Wierzbicki, D., Karwowska, K., Karwowski, W., & Kovarik, V. (2026). From Detection to Functional Analysis: Evaluating Vehicle Detection Models in High-Resolution Earth Observation Imagery. Remote Sensing, 18(13), 2166. https://doi.org/10.3390/rs18132166
Vancouver
Wierzbicki D, Karwowska K, Karwowski W, Kovarik V. From Detection to Functional Analysis: Evaluating Vehicle Detection Models in High-Resolution Earth Observation Imagery. Remote Sensing. 2026;18(13):2166. doi:10.3390/rs18132166
BibTeX
@article{Wierzbicki2026,
author = {Wierzbicki, Damian and Karwowska, Kinga and Karwowski, Wojciech and Kovarik, Vladimir},
title = {From Detection to Functional Analysis: Evaluating Vehicle Detection Models in High-Resolution Earth Observation Imagery},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {13},
pages = {2166},
doi = {10.3390/rs18132166}
}
EUVIMED