EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Target detection and classification via EfficientDet and CNN over unmanned aerial vehicles

Muhammad Ovais Yusuf, Muhammad Hanzla, Naif Al Mudawi, Touseef Sadiq, Bayan Alabdullah, Hameedur Rahman, Asaad Algarni

Frontiers in Neurorobotics · 30.08.2024 · 18

DOI: 10.3389/fnbot.2024.1448538 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Neurorobotics, online erschienen am 30.08.2024. Verfasst von Muhammad Ovais Yusuf und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computing ad AI, Air University, Islamabad, Pakistan. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 118 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Advanced traffic monitoring systems face significant challenges in vehicle detection and classification. Conventional methods often require substantial computational resources and struggle to adapt to diverse data collection methods.

Methods

This research introduces an innovative technique for classifying and recognizing vehicles in aerial image sequences. The proposed model encompasses several phases, starting with image enhancement through noise reduction and Contrast Limited Adaptive Histogram Equalization (CLAHE). Following this, contour-based segmentation and Fuzzy C-means segmentation (FCM) are applied to identify foreground objects. Vehicle detection and identification are performed using EfficientDet. For feature extraction, Accelerated KAZE (AKAZE), Oriented FAST and Rotated BRIEF (ORB), and Scale Invariant Feature Transform (SIFT) are utilized. Object classification is achieved through a Convolutional Neural Network (CNN) and ResNet Residual Network.

Results

The proposed method demonstrates improved performance over previous approaches. Experiments on datasets including Vehicle Aerial Imagery from a Drone (VAID) and Unmanned Aerial Vehicle Intruder Dataset (UAVID) reveal that the model achieves an accuracy of 96.6% on UAVID and 97% on VAID.

Discussion

The results indicate that the proposed model significantly enhances vehicle detection and classification in aerial images, surpassing existing methods and offering notable improvements for traffic monitoring systems.

Schlagwörter

Stichwörter der Autor:innen

deep learningdynamic environmentsmulti-objects recognitionmulti-objects recognition deep learningpath planningremote sensingunmanned aerial vehicles

Autor:innen und Institutionen

  • Faculty of Computing ad AI, Air University, Islamabad, Pakistan.
  • Department of Computer Science, College of Computer Science and Information System, Najran University, Najran, Saudi Arabia.
  • Centre for Artificial Intelligence Research, Department of Information and Communication Technology, University of Agder, Grimstad, Norway.
  • Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
  • Department of Computer Sciences, Faculty of Computing and Information Technology, Northern Border University, Rafha, Saudi Arabia.

Zitieren

APA

Yusuf, M. O., Hanzla, M., Al Mudawi, N., Sadiq, T., Alabdullah, B., Rahman, H., & Algarni, A. (2024). Target detection and classification via EfficientDet and CNN over unmanned aerial vehicles. Frontiers in Neurorobotics, 18. https://doi.org/10.3389/fnbot.2024.1448538

Vancouver

Yusuf MO, Hanzla M, Al Mudawi N, Sadiq T, Alabdullah B, Rahman H, et al. Target detection and classification via EfficientDet and CNN over unmanned aerial vehicles. Frontiers in Neurorobotics. 2024;18. doi:10.3389/fnbot.2024.1448538

BibTeX
@article{Yusuf2024,
  author = {Yusuf, Muhammad Ovais and Hanzla, Muhammad and Al Mudawi, Naif and Sadiq, Touseef and Alabdullah, Bayan and Rahman, Hameedur and Algarni, Asaad},
  title = {Target detection and classification via EfficientDet and CNN over unmanned aerial vehicles},
  journal = {Frontiers in Neurorobotics},
  year = {2024},
  volume = {18},
  doi = {10.3389/fnbot.2024.1448538}
}
Kostenlos starten →