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

Target Classification via Fire Pattern Analysis in Infrared Imagery

적외선 영상 기반 발화 패턴 분석을 통한 표적 분류 알고리즘 연구

  • Dae-hyeok Kwon (Department of Aerospace Engineering, KAIST) ;
  • Minkyu Shin (Department of Aerospace Engineering, KAIST) ;
  • Sky Haneul Lee (Department of Aerospace Engineering, KAIST) ;
  • Han-Lim Choi (Department of Aerospace Engineering, KAIST) ;
  • Jaeuk Kim (Intelligent Software Team, Hanwha System Co., Ltd.) ;
  • Mingi Kim (Intelligent Software Team, Hanwha System Co., Ltd.)
  • 권대혁 (한국과학기술원 항공우주공학과) ;
  • 신민규 (한국과학기술원 항공우주공학과) ;
  • 이하늘 (한국과학기술원 항공우주공학과) ;
  • 최한림 (한국과학기술원 항공우주공학과) ;
  • 김재욱 (한화시스템(주) 지능형 SW팀) ;
  • 김민기 (한화시스템(주) 지능형 SW팀)
  • Received : 2025.04.22
  • Accepted : 2025.08.29
  • Published : 2025.10.05
Download PDF
⟨ Previous Next ⟩

Abstract

To carry out missions effectively in battlefield environments, it is essential to rapidly identify enemy threats and respond through precise analysis. Accordingly, technologies that utilize artificial intelligence to identify and classify targets in real time are being actively researched in modern warfare. In this study, we propose a deep learning-based target classification algorithm that simultaneously ensures real-time performance and high classification accuracy. Time-series data are constructed from infrared imagery and augmented to train the model, and the effectiveness of the proposed algorithm is demonstrated through comparative experiments with various CNN- and RNN-based models.

Keywords

Acknowledgement

이 논문은 2023년도 정부(방위사업청)의 재원으로 국방기술진흥연구소의 지원을 받아 수행된 연구임(No. KRIT-CT-23-004, 복합형 능동방호 기술)

References

  1. S. Seo, K. Kim, J. Kim, S. Cho and S. Park, "Study on Multi-Domain Anti-Drone System in the Ukraine-Russia War," Journal of the Korea Defense Robotics Society, Vol. 2, No. 1, pp. 25-32, 2023.
  2. S. Kim, S. Kwak and J. Shin, "Analysis of Defense Systems Against Drone Threats," Journal of the Korean Convergence Science Society, Vol. 11, No. 11, pp. 287-310, 2022. https://doi.org/10.24826/KSCS.11.11.18
  3. S. Park, J. Park, S. Seo and J. Kim, "Analysis of Combat Effectiveness of Active Protection Systems for Armored Vehicles," Journal of the Korea Academia-Industrial Cooperation Society, Vol. 25, No. 7, pp. 423-432, 2024. https://doi.org/10.5762/KAIS.2024.25.7.423
  4. H. Sak, A. W. Senior and F. Beaufays, "Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling," Interspeech, Vol. 2014, pp. 338-342, 2014.
  5. K. Cho, B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, "Learning phrase representations using RNN encoder-decoder for statistical machine translation," in Proc. 2014 Conf. Empirical Methods in Natural Language Processing(EMNLP), Doha, Qatar, pp. 1724-1734, 2014.
  6. G. Zerveas, S. Jayaraman, D. Patel, A. Bhamidipaty and C. Eickhoff, "A Transformer-Based Framework for Multivariate Time Series Representation Learning," Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 2114-2124, August, 2021.
  7. B. Lim, S. Ö. Arık, N. Loeff and T. Pfister, "Temporal Fusion Transformers for Interpretable Multi-Horizon Time Series Forecasting," International Journal of Forecasting, Vol. 37, No. 4, pp. 1748-1764, 2021. https://doi.org/10.1016/j.ijforecast.2021.03.012
  8. J. Qin and L. Zong, "TS-BERT: A Fusion Model for Pre-trainning Time Series-Text Representations," 2022.
  9. Chen, Y., Jiang, H., Li, C., Jia, X., & Ghamisi, P., "Deep feature extraction and classification of hyperspectral images based on convolutional neural networks," IEEE transactions on geoscience and remote sensing, Vol. 54, No. 10, pp. 6232-6251, 2016. https://doi.org/10.1109/TGRS.2016.2584107
  10. Heinz, D. C., "Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery," IEEE transactions on geoscience and remote sensing, Vol. 39, No. 3, pp. 529-545, 2001. https://doi.org/10.1109/36.911111
  11. Wang, Y., Wang, C., Zhang, H., Dong, Y., & Wei, S., "A SAR dataset of ship detection for deep learning under complex backgrounds," Remote Sensing, Vol. 11, No. 7, p. 765, 2019. https://doi.org/10.3390/rs11070765
  12. McNairn, H., Champagne, C., Shang, J., Holmstrom, D., & Reichert, G., "Integration of optical and Synthetic Aperture Radar(SAR) imagery for delivering operational annual crop inventories," ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 64, No. 5, pp. 434-449, 2009. https://doi.org/10.1016/j.isprsjprs.2008.07.006
  13. Mei, X., & Ling, H., "Robust visual tracking and vehicle classification via sparse representation," IEEE transactions on pattern analysis and machine intelligence, Vol. 33, No. 11, pp. 2259-2272, 2011. https://doi.org/10.1109/TPAMI.2011.66
  14. Wu, X., Hong, D., & Chanussot, J., "UIU-Net: U-Net in U-Net for infrared small object detection," IEEE Transactions on Image Processing, Vol. 32, pp. 364-376, 2022. https://doi.org/10.1109/TIP.2022.3228497
  15. E. Lee, E. Gu, H. Lee, W. Cho and G. Park, "Ground Target Classification Algorithm Based on Multi-Sensor Images," Journal of Korea Multimedia Society, Vol. 15, No. 2, pp. 195-203, 2012. https://doi.org/10.9717/kmms.2012.15.2.195
  16. S. Kim, Y. Choi, W. Jang, M. Han, M. Jeon, H. Lee and S. Hong, "A Study on Missile Impact Image Extraction Using Python and Analysis of Impact Information Using CNN-Based Machine Learning," Journal of the KNST, Vol. 7, No. 4, pp. 438-444, 2024. https://doi.org/10.31818/JKNST.2024.12.7.4.438
  17. M. Moon and W. Lee, "Radar Image Machine Learning for Drone Detection and Classification," Journal of the Korea Institute of Information and Communication Engineering, Vol. 25, No. 5, pp. 619-627, 2021. https://doi.org/10.6109/JKIICE.2021.25.5.619
  18. A. Garg, R. R. Rouf, K. N. Hafiz, M. Sharna and N. Hasan, "Automated Detection, Locking and Hitting a Fast Moving Aerial Object by Image Processing(Suitable for Guided Missile)," IOSR Journal of Electronics and Communication Engineering, Vol. 11, No. 04, pp. 60-68, 2016. https://doi.org/10.9790/2834-1104016068
  19. P. Jindal, H. Gupta, N. Pachauri, V. Sharma and O. P. Verma, "Real-Time Wildfire Detection via Image-Based Deep Learning Algorithm," Soft Computing: Theories and Applications: Proceedings of SoCTA 2020, Volume 2, pp. 539-550, 2021.
  20. X. Chen, et al., "Wildland Fire Detection and Monitoring Using a Drone-Collected RGB/IR Image Dataset," IEEE Access, Vol. 10, pp. 121301-121317, 2022. https://doi.org/10.1109/ACCESS.2022.3222805
  21. N. Ya'acob, M. S. M. Najib, N. Tajudin, A. L. Yusof and M. Kassim, "Image Processing Based Forest Fire Detection Using Infrared Camera," Journal of Physics: Conference Series, Vol. 1768, No. 1, p. 012014, 2021.
  22. Schneider, C. A., Rasband, W. S., & Eliceiri, K. W. (n.d.). ImageJ. National Institutes of Health. https://imagej.net/ij/
  23. M. Menze and A. Geiger, "Object Scene Flow for Autonomous Vehicles," Conference on Computer Vision and Pattern Recognition(CVPR), pp. 3061-3070, 2015.
  24. Z. Wang, W. Yan, and T. Oates, "Time series classification from scratch with deep neural networks: A strong baseline," in Trans. International Joint Conference on Neural Networks(IJCNN), pp. 1578-1585,
  25. X. Zou, Y. Zhang, X. Wang, and X. Wang, "Integration of residual network and convolutional neural network along with various activation functions and global pooling for time series classification," Neurocomputing, Vol. 367, pp. 39-45, 2019. https://doi.org/10.1016/j.neucom.2019.08.023
  26. F. Karim, S. Majumdar, H. Darabi, and S. Chen, "LSTM fully convolutional networks for time series classification," IEEE Access, Vol. 6, pp. 1662-1669, 2017.
  27. N. Elsayed, A. S. Maida, and M. Bayoumi, "Deep gated recurrent and convolutional network hybrid model for univariate time series classification," Int. J. Adv. Comput. Sci. Appl., Vol. 10, No. 5, pp. 654-659, 2019. https://doi.org/10.14569/IJACSA.2019.0100582
  28. N. Mohammadi Foumani, A. Bagnall, F. Petitjean, and M. Schäfer, "Deep learning for time series classification and extrinsic regression: A current survey," ACM Computing Surveys, Vol. 56, No. 9, pp. 1-45, 2024. https://doi.org/10.1145/3649448
  29. K. He, Y. Zhang, M. Li, and X. Liu, "Financial time series forecasting with the deep learning ensemble model," Mathematics, Vol. 11, No. 4, Art. no. 1054, 2023. https://doi.org/10.3390/math11041054
  30. G. Gao, H. Liu, Y. Zhao, and L. Zhang, "CNNBi-LSTM: A complex environment-oriented cattle behavior classification network based on the fusion of CNN and Bi-LSTM," Sensors, Vol. 23, No. 18, Art. no. 7714, 2023. https://doi.org/10.3390/s23187714
  31. M. Cao, X. Li, Y. Wang, and H. Zhang, "A hybrid network integrating MHSA and 1D CNN-Bi-LSTM for interference mitigation in faster-than-Nyquist MIMO optical wireless communications," Photonics, Vol. 11, No. 5, Art. no. 982, 2024. https://doi.org/10.3390/photonics11100982
  32. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, "Attention is all you need," Advances in Neural Information Processing Systems, Vol. 30,
  33. P. Vincent-Lamarre, M. Calderini, and J.-P. Thivierge, "Learning Long Temporal Sequences in Spiking Networks by Multiplexing Neural Oscillations," Front. Comput. Neurosci., Vol. 14, p. 78, 2020. https://doi.org/10.3389/fncom.2020.00078
  34. A. Karanikolos and I. Refanidis, "Encoding Position Improves Recurrent Neural Text Summarizers," Proc. 3rd Int. Conf. on Natural Language and Speech Processing, pp. 142-150, 2019.
  35. C.-C. Kao, R. J. Williams, J. Glass, and Y. Li, "A comparison of pooling methods on LSTM models for rare acoustic event classification," Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), pp. 316-320, 2020.
  36. P. Zhou, Z. Qi, S. Zheng, J. Xu, H. Bao, and B. Xu, "Text classification improved by integrating bidirectional LSTM with two-dimensional max pooling," in Proc. 26th Int. Conf. Computational Linguistics(COLING), Osaka, Japan, pp. 3485-3495, 2016.
  37. D. Hendrycks and K. Gimpel, "A baseline for detecting misclassified and out-of-distribution examples in neural networks," in Proceedings of the International Conference on Learning Representations (ICLR), 2017.