Real-Time Detection of Aircraft Surface Damages Using UAV-Based Aerial Imaging with YOLOv8

Abstract:

The evaluation and walk-around check before an aircraft flight are essential for ensuring aircraft safety. This paper describes a method for creating a system capable of detecting and identifying damages on aircraft surfaces using imagery captured from UAV-based aerial platforms, achieving real-time Internet of Things (IoT) monitoring via other devices. Our aim in this project is to detect skin damage, such as scratches, cracks, and dents, that pose significant threats to the structural integrity and safety of aircraft. Traditional inspection methods are often time-consuming and labor-intensive, making real-time detection systems essential for timely maintenance and safety assurance.The system utilizes UAVs to capture high-resolution aerial images of aircraft surfaces. These images undergo processing by trained machine learning algorithms to detect and classify desired objects in real time at the ground station. The results of the image processing can then be monitored via IoT devices. Experimental results demonstrate the system's effectiveness and efficiency in identifying skin damage on aircraft materials. However, certain limitations have emerged, including restricted coverage of defect types, reduced accuracy with increased class numbers, and substantial hardware requirements. Despite these shortcomings, the system remains promising for enhancing aircraft safety through proactive maintenance and defect detection.

• Periodical: Key Engineering Materials (Volume 997)
• Pages: 83-89
• DOI: https://doi.org/10.4028/p-WphI7a
• Online since: December 2024
• Authors: Kuo Chien Liao*, Jirayu Lau, Wen Duan Fan, Ting Li Chuang, Muhamad Hidayat
• Keywords: Aircraft Structural Damage Detection, Artificial Intelligence (AI), IoT, Real-Time Detection, UAV, YOLOv8

References

[1] Y. Rodriguez-Gallo, B. Escobar-Benitez, and J. Rodriguez-Lainez, "Robust coffee rust detection using uav-based aerial rgb imagery," AgriEngineering, vol. 5, no. 3, pp.1415-1431, 2023.

DOI: 10.3390/agriengineering5030088

[2] Y. Liu, J. Dong, Y. Li, X. Gong, and J. Wang, "A UAV-based aircraft surface defect inspection system via external constraints and deep learning," IEEE Transactions on Instrumentation and Measurement, vol. 71, pp.1-15, 2022.

DOI: 10.1109/tim.2022.3198713

[3] D. Kang and Y.-J. Cha, "Damage detection with an autonomous UAV using deep learning," in Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018, 2018, vol. 10598: SPIE, pp.7-14.

DOI: 10.1117/12.2295961

[4] K.-C. Liao, J.-L. Liou, M. Hidayat, H.-T. Wen, and H.-Y. Wu, "Detection and Analysis of Aircraft Composite Material Structures Using UAV," Inventions, vol. 9, no. 3, p.47, 2024.

DOI: 10.3390/inventions9030047

[5] K.-C. Liao, H.-Y. Wu, and H.-T. Wen, "Using drones for thermal imaging photography and building 3D images to analyze the defects of solar modules," Inventions, vol. 7, no. 3, p.67, 2022.

DOI: 10.3390/inventions7030067

[6] K.-C. Liao and J.-H. Lu, "Using UAV to detect solar module fault conditions of a solar power farm with IR and visual image analysis," Applied Sciences, vol. 11, no. 4, p.1835, 2021.

DOI: 10.3390/app11041835

[7] K. Liao and J. Lu, "Using Matlab real-time image analysis for solar panel fault detection with UAV," in Journal of Physics: Conference Series, 2020, vol. 1509, no. 1: IOP Publishing, p.012010.

DOI: 10.1088/1742-6596/1509/1/012010

[8] K.-C. Liao, H.-T. Wen, and H.-Y. Wu, "Using image analysis techniques to enhance TFT-LCD manufacturing yield through timely detection of PI alignment layer defects," Microelectronics Reliability, vol. 151, p.115259, 2023.

DOI: 10.1016/j.microrel.2023.115259

[9] M. Talib, A. H. Al-Noori, and J. Suad, "YOLOv8-CAB: Improved YOLOv8 for Real-time object detection," Karbala International Journal of Modern Science, vol. 10, no. 1, p.5, 2024.

DOI: 10.33640/2405-609x.3339

[10] Apple, "Apple iPhone 13," 2021. [Online]. Available: https://www.apple.com/iphone-13/.

[11] DJI, "Mavic 2 Enterprise," 2023. [Online]. Available: https://www.dji.com/mavic-2-enterprise.

[12] K. Taylor, "The recording medium: Sensors, ISO, Megapixels & Image Quality explained. Visual Education.," 2023. [Online]. Available: https://visualeducation.com/photography-course/iso-megapixels-sensors/.

[13] K. Taylor, "Understanding aperture & depth of field. Visual Education.," 2023. [Online]. Available: https://visualeducation.com/photography-course/aperture-depth-of-field/.

[14] B. Dwyer, Nelson, J., Hansen, T., et. al., "Roboflow (Version 1.0). computer vision.," 2024. [Online]. Available: https://roboflow.com.

[15] G. Jocher, Chaurasia, A., & Qiu, J., "Ultralytics YOLO (Version 8.0.0)," 2023. [Online]. Available: https://github.com/ultralytics/ultralytics.

[16] Y. Donia, "Aircraft Damage Detection Dataset," 2023. [Online]. Available: https://universe.roboflow.com/youssef-donia-fhktl/aircraft-damage-detection-1j9qk.

[17] T. Nguyen, "Roboflow Universe.," 2023. [Online]. Available: https://universe.roboflow.com/tra-nguyen-xysqe/1207_crack_seg.

[18] PyTorch., "torch.save.," 2024. [Online]. Available: https://pytorch.org/docs/stable/generated/ torch.save.html.