EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FSSA-Det: A Fixed-Support Supervision Adaptation Framework for Vehicle Detection in Satellite Videos

Huang Zhang, Lina Xu, Yuhang Ke, Hao Li

Applied Sciences · 15.11.2026 · 16 (22) · 11318

DOI: 10.3390/app162211318 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 15.11.2026. Verfasst von Huang Zhang und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2025 University Student Independent Innovation Funding Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vehicle detection in satellite videos is challenging because of the small size of vehicles, low contrast, and complex backgrounds. In sparse detectors trained with center-based supervision, output nodes may be present within a vehicle’s bounding box while none exist at its center, leaving these useful nodes without appropriate positive supervision. To address this supervision mismatch, we propose FSSA-Det, a fixed-support supervision adaptation framework that improves vehicle detection by adjusting supervision at existing sparse nodes. The Support-Aligned Appearance Residual (SAAR) module samples local image features at the output coordinates to enhance sparse spatiotemporal features. When a vehicle center has no corresponding output node, Fixed-Support Supervision Adaptation (FSSA) removes conflicting negative heatmap supervision from selected in-box nodes and provides supplementary positive supervision to geometrically matched candidates. Positive–Negative Candidate Discrimination (PNCD) distinguishes vehicle candidates from high-response background candidates through response ranking and background suppression. On the seven VISO test videos, FSSA-Det achieves a macro-averaged F1 score of 81.63%, exceeding the baseline by 4.82 percentage points. Ablation studies further show that FSSA improves vehicle detection recall by adapting supervision at existing output locations.

Förderung

  • 2025 University Student Independent Innovation Funding Program

Zitieren

APA

Zhang, H., Xu, L., Ke, Y., & Li, H. (2026). FSSA-Det: A Fixed-Support Supervision Adaptation Framework for Vehicle Detection in Satellite Videos. Applied Sciences, 16(22), 11318. https://doi.org/10.3390/app162211318

Vancouver

Zhang H, Xu L, Ke Y, Li H. FSSA-Det: A Fixed-Support Supervision Adaptation Framework for Vehicle Detection in Satellite Videos. Applied Sciences. 2026;16(22):11318. doi:10.3390/app162211318

BibTeX
@article{Zhang2026,
  author = {Zhang, Huang and Xu, Lina and Ke, Yuhang and Li, Hao},
  title = {FSSA-Det: A Fixed-Support Supervision Adaptation Framework for Vehicle Detection in Satellite Videos},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {22},
  pages = {11318},
  doi = {10.3390/app162211318}
}
Kostenlos starten →