Real-Time Vehicles Detection Using a Tello Drone with YOLOv5 Algorithm

Keywords: Tello drone, you only look once v5, Roboflow, intersection over union, ultralytics

Abstract

Incorporating Unmanned Aerial Vehicles (UAVs) within Artificial Intelligence systems has given rise to an essential and academically significant approach in the domain of vehicle detection. This study introduces a real-time vehicle detection framework leveraging the you only look once (YOLO) algorithm for precise identification of vehicles, employing the camera on the DJI Tello drone. The research is underpinned by a rich dataset encompassing approximately 2000 images, meticulously annotated with the respective vehicle angles. The framework’s innovation lies in its comprehensive training regimen, encompassing all angles of vehicles: Vehicle-front, vehicle-rear, vehicle-above, and vehicle-sides. This holistic approach aims to yield a model capable of accurately identifying and tracking vehicles from a multitude of viewing angles. The choice of the YOLO algorithm, further enhanced by Ultralytics HUB, ensures the robustness and accuracy required for the detection of moving objects. The model’s capability to effectively track objects is a testament to the algorithm’s efficacy. In assessing the framework’s performance, we employed a comprehensive set of evaluation parameters, including mean average precision, precision, recall, and F1 score. This research not only underscores the practicality of UAVs in the field of artificial intelligence but also highlights the excellence achieved in real-time vehicle detection.

Downloads

Download data is not yet available.

Author Biography

Shalaw M. Abdallah, Department of Software Engineering, Koya University, Kurdistan Region, Iraq

Shalaw M. Abdallahfrom is an assistant lecturer at the Deprtment of Software Engineering, Koya University. His research is drones and  animation.

References

J. Lu, C. Ma, L. Li, X. Xing, Y. Zhang, Z. Wang and J. Xu. A vehicle detection method for aerial image based on YOLO. Journal of Computer and Communications, vol. 6, pp. 98-107, 2018.

J. Nelson and J. Solawetz. Responding to the Controversy about YOLOv5. Roboflow Blog, 2020. Available from: https://blog.roboflow.com/yolov4-versus-yolov5 [Last accessed on 2023 Jan10].

W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu and A. C. Berg. SSD: Single Shot Multibox Detector. In: Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016, Proceedings, Part I 14. Springer International Publishing, Berlin, pp. 21-37, 2016. Available from: https://arxiv.org/pdf/1512.02325.pdf%22source%22 [Last accessed on 2023 Jan 02].

J. Redmon, S. Divvala, R. Girshick and A. Farhadi. You Only Look Once: Unified, Real-time Object Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016. Available from: https://arxiv.org/abs/1506.02640 [Last accessed on 2023 Jan 07].

J. Yu, J. Xu, Y. Chen, W. Li, Q. Wang, B. I. Yoo and J. J. Han. Learning Generalized Intersection Over Union for Dense Pixelwise Prediction. In: International Conference on Machine Learning, pp. 12198-12207, 2021. Available from: https://shorturl.at/jBGIN [Last accessed on 2023 Jan 14].

H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese. Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern recognition, pp. 658- 666, 2019. Available from: https://arxiv.org/abs/1902.09630 [Last accessed on 2023 Jan 14].

Z. Huang, H. Zhao, J. Zhan and H. Li. A multivariate intersection over union of SiamRPN network for visual tracking. The Visual Computer, Vol. 38, pp. 2739-2750, 2022.

H. K. Jung and G. S. Choi. Improved yolov5: Efficient object detection using drone images under various conditions. Applied Sciences, Vol. 12, no. 14, p. 7255, 2022.

I. Katsamenis, E. E. Karolou, A. Davradou, E. Protopapadakis, A. Doulamis, N. Doulamis and D. Kalogeras. TraCon: A novel dataset for real-time traffic cones detection using deep learning. In: Novel and Intelligent Digital Systems Conferences. Springer International Publishing, Cham, pp. 382-391, 2022. Available from: https:// arxiv.org/pdf/2205.11830.pdf [Last accessed on 2023 Jan 12].

C. Y. Wang, H. Y. Mark Liao, Y. H. Wu, P. Y. Chen, J. W. Hsieh and I. H Yeh. CSPNet: A New Backbone that Can Enhance Learning Capability of CNN. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390-391. 2020. Available from: https://arxiv.org/abs/1911.11929 [Last accessed on 2023 Feb 06].

K. Wang, J. H. Liew, Y. Zou, D. Zhou and J. Feng. Panet: Few-shot Image Semantic Segmentation with Prototype Alignment. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9197-9206, 2019.

M. Horvat, L. Jelečević and G. Gledec. A Comparative Study of YOLOv5 Models Performance for Image Localization and Classification. In: Proceedings of theCentral European Conference on Information and Intelligent Systems. Faculty of Organization and Informatics Varazdin, pp. 349-356, 2022. Available from: https://shorturl.at/hFPT1 [Last accessed on 2023 Feb 16].

D. Dlužnevskij, P. Stefanovič and S. Ramanauskaite. Investigation of YOLOv5 efficiency in iPhone supported systems. Baltic Journal of Modern Computing, Vol. 9, pp. 333-334, 2021.

S. Mshir. Vehicle Detection Dataset. Roboflow Universe, 2023. Available from: https://universe.roboflow.com/shalaw/vehicledetection-rfmsje [Last accessed on 2023 Feb].

S. Karslioglu. Saving and Loading Models Across Devices in PyTorch. PyTorch Organization, 2023. Available from: https://pytorch.org/tutorials/recipes/recipes/save_load_across_devices. html [Last accessed on 2023 Feb 02].

P. K. Yadav, J. A. Thomasson, S. W. Searcy, R. G. Hardin, U. Braga-Neto, S. C. Popescu, D. E. Martin, R. Rodriguez, K. Meza, J. Enciso, J. S. Diaz and T. Wang. Assessing the performance of YOLOv5 algorithm for detecting volunteer cotton plants in corn fields at three different growth stages. Artificial Intelligence in Agriculture, Vol. 6, pp. 292-303, 2022.

J. Lowe. Precision and Recall in Machine Learning. Roboflow Blog, 2022. Available from: https://blog.roboflow.com/precision-andrecall [Last accessed on 2023 Feb 03].

F. Damien, M. U. Javaid, N. Posocco and S. Tihon. Anomaly Detection: How to Artificially Increase Your F1-Score with a Biased Evaluation Protocol. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer International Publishing, Cham, pp. 3-18, 2021. Available from: https://arxiv.org/pdf/2106.16020.pdf [Last accessed on 2023 Feb 12].

J. Solawetz. What is Mean Average Precision (mAP) in Object Detection? Roboflow Blog, 2020. Available from: https://blog. roboflow.com/mean-average-precision [Last accessed on 2023 Feb 14].

Q. H. Phan, V. T. Nguyen, C. H. Lien, T. P. Duong, M.T. K. Hou and N. B. Le. Classification of tomato fruit using Yolov5 and convolutional neural network models. Plants, Vol. 12, p. 790, 2023.

Published
2024-01-20
How to Cite
1.
Abdallah S. Real-Time Vehicles Detection Using a Tello Drone with YOLOv5 Algorithm. cuesj [Internet]. 20Jan.2024 [cited 24Apr.2024];8(1):1-. Available from: https://journals.cihanuniversity.edu.iq/index.php/cuesj/article/view/1010
Section
Research Article