Abstract

This paper investigates the development of a real-time image-based object detection and tracking system for an unmanned aerial vehicle (UAV). The overall UAV architecture, including the autopilot, sensor suite, and software components, is analyzed [1]. The use of deep learning–based computer vision models for real-time video processing is highlighted [2]. A YOLO-family model is employed for object detection, while the ByteTrack algorithm is used for object tracking [3]. A video acquisition and frame-processing pipeline is implemented using OpenCV [4], and system performance is evaluated in real time using FPS and latency metrics. Experimental results show that, through model and computational optimization, stable near–real-time performance can be achieved. The proposed approach enables efficient decision-making for UAV-based monitoring, surveillance, and security applications.

References

[1]. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems (NIPS), vol. 25, pp. 1097–1105, 2012.
[2]. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, real-time object detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 779–788.
[3]. J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
[4] G. Jocher et al., “YOLOv8: Ultralytics YOLO,” 2023.
[Online]. Available: https://github.com/ultralytics/ultralytics
[5]. Y. Zhang, P. Sun, Y. Jiang, D. Yu, F. Weng, and Z. Yuan, “ByteTrack: Multi-object tracking by associating every detection box,” in Proc. European Conf. Computer Vision (ECCV), Tel Aviv, Israel, 2022, pp. 1–17.
[6]. G. Bradski, “The OpenCV Library,” Dr. Dobb’s Journal of Software Tools, 2000.
[7]. S. Shah, D. Dey, C. Lovett, and A. Kapoor, “AirSim: High-fidelity visual and physical simulation for autonomous vehicles,” in Field and Service Robotics, Springer, 2018, pp. 621–635.
[8]. M. Quigley et al., “ROS: An open-source robot operating system,” in Proc. IEEE Int. Conf. Robotics and Automation Workshop (ICRA), Kobe, Japan, 2009.
[9]. L. Heng, S. Lee, and M. Pollefeys, “Self-calibration and visual SLAM for unmanned aerial vehicles,” Robotics and Autonomous Systems, vol. 61, no. 2, pp. 111–125, 2013.
[10]. S. Thrun, W. Burgard, and D. Fox, Probabilistic Robotics. Cambridge, MA, USA: MIT Press, 2005.
[11]. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
[13]. J. Tursunov, A. Narimonova, B. Hamroev, S. Bobokulov, et al., “Custom object segmentation by training R-CNN,” in Intelligent Human Computer Interaction, Lecture Notes in Computer Science
[14]. Sh. R. Davronov and Sh. R. Boboqulov, “Improving real-time face recognition accuracy and processing speed using the Non-Maximum Suppression algorithm,” Innovative Technologies: Scientific and Technical Journal, no. 3/59, pp. 111–116, 2025.