Version 1
: Received: 1 December 2022 / Approved: 2 December 2022 / Online: 2 December 2022 (10:33:02 CET)
Version 2
: Received: 11 January 2023 / Approved: 12 January 2023 / Online: 12 January 2023 (10:46:25 CET)
How to cite:
Khan, M.U.; Dil, M.; Misbah, M.; Orakzai, F.A.; Alam, M.Z.; Kaleem, Z. TransLearn-YOLOx: Improved-YOLO with Transfer Learning for Fast and Accurate Multiclass UAV Detection. Preprints2022, 2022120049. https://doi.org/10.20944/preprints202212.0049.v2
Khan, M.U.; Dil, M.; Misbah, M.; Orakzai, F.A.; Alam, M.Z.; Kaleem, Z. TransLearn-YOLOx: Improved-YOLO with Transfer Learning for Fast and Accurate Multiclass UAV Detection. Preprints 2022, 2022120049. https://doi.org/10.20944/preprints202212.0049.v2
Khan, M.U.; Dil, M.; Misbah, M.; Orakzai, F.A.; Alam, M.Z.; Kaleem, Z. TransLearn-YOLOx: Improved-YOLO with Transfer Learning for Fast and Accurate Multiclass UAV Detection. Preprints2022, 2022120049. https://doi.org/10.20944/preprints202212.0049.v2
APA Style
Khan, M.U., Dil, M., Misbah, M., Orakzai, F.A., Alam, M.Z., & Kaleem, Z. (2023). TransLearn-YOLOx: Improved-YOLO with Transfer Learning for Fast and Accurate Multiclass UAV Detection. Preprints. https://doi.org/10.20944/preprints202212.0049.v2
Chicago/Turabian Style
Khan, M.U., Muhammad Zeshan Alam and Zeeshan Kaleem. 2023 "TransLearn-YOLOx: Improved-YOLO with Transfer Learning for Fast and Accurate Multiclass UAV Detection" Preprints. https://doi.org/10.20944/preprints202212.0049.v2
Abstract
The emergence of unmanned aerial vehicles (UAVs) raised multiple concerns, given their potential for malicious misuse in unlawful acts Vision-based counter-UAV applications offer a reliable solution compared to acoustic and radio frequency-based solutions because of their high detection accuracy in diverse weather conditions. The existing solutions work well on trained datasets, but their accuracy is relatively low for real-time detection. In this paper, we model deep learning-empowered solutions to improve the multi-class UAV's classification performance using single-shot object detection algorithms YOLOv5 and YOLOv7. The transfer learning is employed for performance improvement and rapid training with improved results. We customized a multi-class dataset containing multi-rotor, fixed-wing, and single-rotor UAVs in challenging weather conditions. Experiments show that the integration of transfer learning has achieved good results, with an overall best average-classification precision of 94\%, an average recall of 93.1\%, a mAP$@$0.5 average of 95.3\%, and an average F1 score of 92.33\%. The dataset and code are available as an open source: https://github.com/ZeeshanKaleem/YOLOV5-Large-vs-YOLOV7.git
Keywords
UAV detection; deep learning; YOLOv5; YOLOv7
Subject
Computer Science and Mathematics, Software
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Commenter: Zeeshan Kaleem
Commenter's Conflict of Interests: Author