Author(s)

JianJun Song

Affiliation(s)

Shanghai Technical Institute of Electronics Information, Shanghai 201411, China.

Corresponding Author

JianJun Song

ABSTRACT

When conducting long-range wireless charging and monitoring of Unmanned Aerial Vehicles (UAVs) in the air, remote identification and tracking of the drones in the air are required. To address this issue, a deep learning-based algorithm for aerial UAVs identification and tracking is proposed. The YOLO algorithm is utilized for UAVs identification in the air, and the Deep Sort algorithm is used for tracking the identified UAVs. A model and training dataset are constructed, and the deep learning model is trained. The trained model is then invoked to verify the identification and tracking effectiveness of the UAVs in the air.

KEYWORDS

Deep learning visual algorithms; YOLO; Deep SORT; UAVs identification and tracking

CITE THIS PAPER

JianJun Song. Identification and tracking of aerial UAVS based on deep learning visual algorithms. Multidisciplinary Journal of Engineering and Technology. 2024, 1(1): 17-28. DOI: 10.61784/mjet3005.

REFERENCES

[1] Naing KM, Zakeri A, Iliev O. Wireless energy transfer to long distance flying intelligent Unmanned Aerial Vehicles (UAVs) using reactive power transfer techniques. Technol, 2020, 7(9), 2458-9403.

[2] Chittoor PK, Chokkalingam B, Mihet-Popa L. A review on UAV wireless charging: Fundamentals, applications, charging techniques and standards. IEEE access, 2021, 9, 69235-69266.

[3] Sheu BH, Chiu CC, Lu WT, Lien CC, Liu TK, Chen WP. Dual-axis rotary platform with UAV image recognition and tracking. Microelectronics Reliability, 2019, 95, 8-17.

[4] Samadzadegan F, Dadrass Javan F, Ashtari Mahini F, Gholamshahi M. Detection and recognition of drones based on a deep convolutional neural network using visible imagery. Aerospace, 2022, 9(1), 31.

[5] Dadrass Javan F, Samadzadegan F, Gholamshahi M, Ashatari Mahini F. A modified YOLOv4 Deep Learning Network for vision-based UAV recognition. Drones, 2022, 6(7), 160.

[6] Sun H, Wang X, Cao Z, Bai F, Wang X, Hao Y, Wang J. Deep learning-based counter-UAV early warning neural network. Science Technology and Engineering, 2021, 21(22), 9461-9469.

[7] Shi Y, Zhu J, Ling Z. Research on UAV detection algorithm based on feature-enhanced YOLOv4. Journal of Electronic Measurement and Instrumentation, 2022, 36(7), 16-23.

[8] Durve M, Orsini S, Tiribocchi A, Montessori A, Tucny JM, Lauricella M, ... Succi S. Benchmarking YOLOv5 and YOLOv7 models with DeepSORT for droplet tracking applications. The European Physical Journal E, 2023, 46(5), 32. 

[9] Xie T, Yao X. Smart logistics warehouse moving-object tracking based on yolov5 and deepsort. Applied Sciences, 2023, 13(17), 9895.

[10] Bai T. Multiple Object Tracking Based on YOLOv5 and Optimized DeepSORT Algorithm. In Journal of Physics: Conference Series. IOP Publishing, 2023, 2547,012022.

[11] Huang Y, Xiao D, Liu J, Tan Z, Liu K, Chen M. An improved pig counting algorithm based on YOLOv5 and DeepSORT model. Sensors, 2023, 23(14), 6309.

[12] Kumar S, Singh SK, Varshney S, Singh S, Kumar P, Kim BG, Ra IH. Fusion of deep sort and Yolov5 for effective vehicle detection and tracking scheme in real-time traffic management sustainable system. Sustainability, 2023, 15(24), 16869.

[13] Razzok M, Badri A, El Mourabit I, Ruichek Y, Sahel A. Pedestrian detection and tracking system based on Deep-SORT, YOLOv5, and new data association metrics. Information, 2023, 14(4), 218.

[14] Ma L, Meng D, Zhao S, An B. Visual localization with a monocular camera for unmanned aerial vehicle based on landmark detection and tracking using YOLOv5 and DeepSORT. International Journal of Advanced Robotic Systems, 2023, 20(3), 17298806231164831.

[15] Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, 779-788.