Detecting Objects in Aerial Photographs using Neural Network Techniques
Article Sidebar
Main Article Content
Abstract
This article discusses the study of aerial image analysis obtained from Unmanned Aerial Vehicles (UAVs) using the principles of artificial neural networks for image recognition. In this study, the author reviews the literature on image analysis for object detection and explores which models are suitable for the task of object detection in aerial images. The author selects the YOLO, RetinaNet, and Fast R-CNN detection models after careful consideration. Through experimentation and study, the article reveals that when detecting objects in aerial images captured by UAVs, it is crucial to choose a detection model that aligns well with the equipment used for image capture. The experimental results show that utilizing the YOLO model yields a mean Average Precision (mAP) of up to 58.5% and a processing speed of 158.13 frames per second. These results highlight the superior accuracy and speed of object detection compared to other models tested with aerial images captured by unmanned aerial vehicles.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Journal of TCI is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence, unless otherwise stated. Please read our Policies page for more information...
References
Q. M. Chung, T. D. Le, T. V. Dang, N. D. Vo, T. V. Nguyen, and K. Nguyen, "Data Augmentation Analysis in Vehicle Detection from Aerial Videos," in 2020 RIVF Int. Conf. Comput. Commun.Technol. (RIVF), Ho Chi Minh City, Vietnam, 2020, pp. 1-3, doi: 10.1109/RIVF48685.2020.9140740.
S. Ali, A. Siddique, H. F. Ates, and B. K. Güntürk, "Improved YOLOv4 for Aerial Object Detection," in 2021 29th Signal Process. Commun. Appl. Conf. (SIU), Istanbul, Turkey, 2021, pp. 1 - 4, doi: 10.1109/SIU53274.2021.9478027.
Y. Zuo, J. Yang, Z. Zhu, R. Li, Y. Zhou, and Y. Zheng, "Real-Time Semantic Seg- Defence Technology Academic Journal, Volume 5 Issue 12 / July - December 2023 11 mentation of Aerial Videos Based on Bilat eral Segmentation Network," in 2021 IEEE Int. Geosci. Remote Sens.Symp. (IGARSS), Brussels, Belgium, 2021, pp. 2763-2766, doi: 10.1109/IGARSS47720.2021.9554952.
I. Yurchuk, V. Kovdrya, and L. Bilyanska, "Segmentation of Digital Images of Aerial Photography," in 2019 IEEE 5th Int. Conf. Actual Problems U n m a n n e d A e r i a l V e h i c l e s Develop. (APUAVD), Kiev, Ukraine, 2019, pp. 258-261, doi: 10.1109/ APUAVD47061.2019.8943841.
G. - S. Xia et al., “DOTA: A Large-scale Dataset for Object Detection in Aerial Images,” in IEEE Conf. Comput. Vision Pattern Recognit. (CVPR), Salt Lake City , UT, USA, 2018, pp. 3974 - 3983.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in 2016 IEEE Conf. Comput. Vision Pattern Recognit. (CVPR), Las Vegas, NV, USA, 2016, pp. 779-788. doi: 10.1109/CVPR.2016.91.
T. -Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, "Focal Loss for Dense Object Detection," in IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 2, pp. 318-327, Feb. 2020, doi: 10.1109/TPAMI. 2018. 2858826.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detectionwith Region Proposal Networks,” in Adv. Neural Inf. Process. Syst. 28 (NIPS 2015), C. Cortes, N. Lawrence, D. Lee, M. Sugiyama and R. Garnett, Eds. 2015, pp. 1 - 9.
K. O’Shea and R. Nash, “An Introduction to Convolutional Neural Networks,” 2015, arXiv:1511.08458.
J. Sun, B. Li, Y. Jiang, and C.-y. Wen, “A Camera-Based Target Detection and Positioning UAV System for Search and Rescue (SAR) Purposes,” Sensors, vol. 16, no. 11, p. 1778, 2016, doi: 10.3390/ s16111778.