EUVIMEDEUVIMED entdecken
Crossref

Two-Stage Framework for Specialty Vehicles Detection and Classification: Toward Intelligent Visual Surveillance of Airport Surface

Meng Ding, Wenhui Zhou, Yiming Xu, Yubin Xu

IEEE Transactions on Aerospace and Electronic Systems · 2024-04 · 60 (2) · 1912-1923

DOI: 10.1109/taes.2023.3342797 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2024-04. Verfasst von Meng Ding und 3 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, Nanjing University of Aeronautics and Astronautics.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intelligent visual surveillance (IVS) is being gradually introduced into the field of airport surface surveillance. The first task of IVS is to detect and recognize objects moving on the airport surface. Specialty vehicles play a considerable role in airport ground handling processes and are considerably monitored targets. Because specialty vehicles have diverse appearances and irregular shapes, pixel-level detection would enable them to be targeted more accurately. Specialty vehicles on the surface undertake different jobs in airport ground handling processes, and therefore subcategory classification would more precisely determine the function of these specialty vehicles. Moreover, pixel-level detection and subcategory classification are very useful for detecting key milestone nodes of airport ground handling processes. Thus, in this article, a two-stage framework for specialty vehicle pixel-level detection and subcategory classification for IVS of the airport surface is exploited, which seamlessly integrates state-of-the-art algorithms and techniques, and consists of two segmentation stages (coarse mask generation and refined mask generation). Furthermore, to evaluate related methods, a dataset of airport surface specialty vehicles is established, which contains four types of representative specialty vehicles and corresponding accurate mask labels. All samples in the dataset were captured from surveillance videos of civil airports. Experimental results on the dataset clearly demonstrate that the proposed framework performed favorably compared with the classic instance segmentation methods and achieved pixel-level detection and subcategory classification of specialty vehicles for airport surface surveillance.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Nanjing University of Aeronautics and Astronautics
  • Ministry of Industry and Information Technology
  • Opening Project of Civil Aviation Satellite Application Engineering Technology Research
  • Aeronautical Science Foundation of China

Zitieren

APA

Ding, M., Zhou, W., Xu, Y., & Xu, Y. (2024). Two-Stage Framework for Specialty Vehicles Detection and Classification: Toward Intelligent Visual Surveillance of Airport Surface. IEEE Transactions on Aerospace and Electronic Systems, 60(2), 1912-1923. https://doi.org/10.1109/taes.2023.3342797

Vancouver

Ding M, Zhou W, Xu Y, Xu Y. Two-Stage Framework for Specialty Vehicles Detection and Classification: Toward Intelligent Visual Surveillance of Airport Surface. IEEE Transactions on Aerospace and Electronic Systems. 2024;60(2):1912-1923. doi:10.1109/taes.2023.3342797

BibTeX
@article{Ding2024,
  author = {Ding, Meng and Zhou, Wenhui and Xu, Yiming and Xu, Yubin},
  title = {Two-Stage Framework for Specialty Vehicles Detection and Classification: Toward Intelligent Visual Surveillance of Airport Surface},
  journal = {IEEE Transactions on Aerospace and Electronic Systems},
  year = {2024},
  volume = {60},
  number = {2},
  pages = {1912--1923},
  doi = {10.1109/taes.2023.3342797}
}
Kostenlos starten →