Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Keypoint-Based Geometric Anomaly Analysis Method for Antennas Using an EO Sensor Mounted on an Unmanned Vehicle

무인이동체 탑재 EO 센서를 활용한 키포인트 기반 안테나 기하학적 이상 분석 기법

  • Yusun Ahn (Electronics and Telecommunications Research Institute, Defense & Safety Intelligence Research Section) ;
  • ihun Jeon (Electronics and Telecommunications Research Institute, Defense & Safety Intelligence Research Section) ;
  • Kangbok Lee (Electronics and Telecommunications Research Institute, Defense & Safety Intelligence Research Section)
  • 안유선 (한국전자통신연구원 국방안전지능화연구실) ;
  • 전지훈 (한국전자통신연구원 국방안전지능화연구실) ;
  • 이강복 (한국전자통신연구원 국방안전지능화연구실)
  • Received : 2025.08.20
  • Accepted : 2025.10.23
  • Published : 2025.12.05
Download PDF
⟨ Previous Next ⟩

Abstract

This study proposes a keypoint-based structural anomaly analysis system using Electro-Optical(EO) sensors mounted on unmanned ground vehicles. Unlike conventional object detection approaches, which struggle to interpret fine-grained structural deviations, the proposed method extracts keypoints of components and evaluates their geometric relationships-such as relative height ratios and tilt angles-to assess structural integrity. A three-stage pipeline consisting of object detection, keypoint detection, and post-processing validation is implemented. Experiments under various rotated conditions (0°, 90°, 135°, and 180°) show that the proposed method achieves error rates below 0.5 %, significantly outperforming conventional bounding box-based methods, which show over 50 % error. The system also demonstrates strong robustness against occlusion, viewpoint variation, and partial visibility. These results highlight the system's potential for real-time autonomous diagnostics, predictive maintenance, and quantitative evidence-based monitoring in dynamic field environments.

Keywords

Acknowledgement

본 연구는 대한민국 정부(산업통상자원부 및 방위사업청) 재원으로 민군협력진흥원에서 수행하는 민군 기술협력사업의 연구비 지원으로 수행되었습니다. (과제번호 23-CM-TC-13)

References

  1. D. Perterson, et. al., "Radome Boresight Error and Compensation Techniques for Electronically Scanned Arrays," AIAA 93-2648, 2nd Annual AIAA SDIO Technology Conference(B), Vol. 23, No. 1, pp. 123-180, June, 1993.
  2. H. Chen, Y. Lyu, J. Shi and W. Zhang, "UAV anomaly detection method based on convolutional autoencoder and support vector data description with 0/1 soft-margin loss," Drones, Vol. 8, No. 10, p. 534, 2024.
  3. A. V. R. Katkuri, H. Madan, N. Khatri, A. S. H. Abdul-Qawy and K. S. Patnaik, "Autonomous UAV navigation using deep learning-based computer vision frameworks: A systematic literature review," Array, Vol. 23, p. 100361, 2024.
  4. S. Khan, C. F. Liew, T. Yairi and R. McWilliam, "Unsupervised anomaly detection in unmanned aerial vehicles," Applied Soft Computing, Vol. 83, p. 105650, 2019.
  5. M. Jeon, J. Moon, S. Jeong and K. Y. Oh, "Autonomous flight strategy of an unmanned aerial vehicle with multimodal information for autonomous inspection of overhead transmission facilities," Computer‐Aided Civil and Infrastructure Engineering, Vol. 39, No. 14, pp. 2159-2186, 2024.
  6. R. Khanam and M. Hussain, "YOLOv11: An overview of the key architectural enhancements," arXiv preprint, arXiv:2410.17725, 2024.
  7. R. Girshick, "Fast R-CNN," Proc. IEEE Int. Conf. Computer Vision, pp. 1440-1448, 2015.
  8. G. D. Raj and B. Prabadevi, "Enhancing surface detection: A comprehensive analysis of various YOLO models," Heliyon, Vol. 11, No. 3, 2025.
  9. J. H. Tian, X. F. Feng, F. Li, Q. L. Xian, Z. H. Jia and J. L. Liu, "An improved YOLOv5n algorithm for detecting surface defects in industrial components," Scientific Reports, Vol. 15, No. 1, p. 9756, 2025.
  10. G. Pang, C. Shen, L. Cao and A. V. D. Hengel, "Deep learning for anomaly detection: A review," ACM Computing Surveys, Vol. 54, No. 2, pp. 1-38, 2021.
  11. Y. Yajing and D. Zhongjian, "Abnormal behavior detection in crowd scene using YOLO and Conv-AE," Proc. 2021 33rd Chinese Control and Decision Conf. (CCDC), pp. 1720-1725, May 2021.
  12. Y. Choi and I. Joe, "Motor fault diagnosis and detection with convolutional autoencoder(CAE) based on analysis of electrical energy data," Electronics, Vol. 13, No. 19, p. 3946, 2024.
  13. D. Maji, S. Nagori, M. Mathew and D. Poddar, "YOLO-Pose: Enhancing YOLO for multi-person pose estimation using object keypoint similarity loss," Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, pp. 2637-2646, 2022.
  14. Ultralytics, YOLOv11: real-time end-to-end object detection, https://github.com/ultralytics/ultralytics, Accessed 6 Oct 2025.
  15. J. Wang, S. Tan, X. Zhen, S. Xu, F. Zheng, Z. He, and L. Shao, "Deep 3D human pose estimation: A review," Computer Vision and Image Understanding, Vol. 210, p. 103225, 2021.
  16. N. D. Reddy, M. Vo and S. G. Narasimhan, "Carfusion: Combining point tracking and part detection for dynamic 3D reconstruction of vehicles," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1906-1915, 2018.
  17. M. Vlaminck, R. Heidbuchel, W. Philips, and H. Luong, "Region-based CNN for anomaly detection in PV power plants using aerial imagery," Sensors, Vol. 22, No. 3, p. 1244, 2022.
  18. M. Siemon, T. B. Moeslund, B. Norton, and K. Nasrollahi, "Bounding boxes and probabilistic graphical models: video anomaly detection simplified," In DAGM German Conference on Pattern Recognition, Cham: Springer Nature Switzerland, pp. 255-269. 2024.