EUVIMEDEUVIMED entdecken
Crossref

A YOLO Analysis for Vehicle Recognition - Detection Improvements, Cropping Strategies and Cascading Architecture

Andrei-Gabriel Nascu, Daniel Gheorghe Gagiu, Dan Selisteanu

Annals of the University of Craiova Mathematics and Computer Science Series · 30.06.2026 · 53 (1) · 291-309

DOI: 10.52846/ami.v53i1.2386 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of the University of Craiova Mathematics and Computer Science Series, online erschienen am 30.06.2026. Verfasst von Andrei-Gabriel Nascu und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the development of high-resolution cameras and enhanced storage devices, image datasets are increasingly captured with higher spatial dimensions. Many modern object detector architectures, such as the YOLO family, typically operate at a 640x640 resolution. When training on high-resolution images, the rescaling process can drastically reduce the region of interest, especially for low- or medium-sized objects far from the camera. To analyze the impact of rescaling, a six-vehicle dataset was constructed from high-resolution images. An automated preprocessing pipeline is built, that crops each car region, enforcing a minimum size of 640x640 by symmetrically expanding the margins. A refactoring process was applied to the new set of images, resulting in a new dataset centered on the region of interest. A YOLOv10 model was trained for each dataset, with the cropped dataset achieving a higher mAP50 of 0.995 compared to the uncropped version's 0.987. A cascading multilevel model employing both YOLO models was further proposed, with the first model analyzing the initial high-resolution image at a coarser level, cropping the vehicle area, and sending it to the second YOLO model for fine-level analysis. This architecture highlights the importance of preserving fine, detailed features that would otherwise be lost during scaling.

Zitieren

APA

Nascu, A., Gagiu, D. G., & Selisteanu, D. (2026). A YOLO Analysis for Vehicle Recognition - Detection Improvements, Cropping Strategies and Cascading Architecture. Annals of the University of Craiova Mathematics and Computer Science Series, 53(1), 291-309. https://doi.org/10.52846/ami.v53i1.2386

Vancouver

Nascu A, Gagiu DG, Selisteanu D. A YOLO Analysis for Vehicle Recognition - Detection Improvements, Cropping Strategies and Cascading Architecture. Annals of the University of Craiova Mathematics and Computer Science Series. 2026;53(1):291-309. doi:10.52846/ami.v53i1.2386

BibTeX
@article{Nascu2026,
  author = {Nascu, Andrei-Gabriel and Gagiu, Daniel Gheorghe and Selisteanu, Dan},
  title = {A YOLO Analysis for Vehicle Recognition - Detection Improvements, Cropping Strategies and Cascading Architecture},
  journal = {Annals of the University of Craiova Mathematics and Computer Science Series},
  year = {2026},
  volume = {53},
  number = {1},
  pages = {291--309},
  doi = {10.52846/ami.v53i1.2386}
}
Kostenlos starten →