Structural Representation Learning for Thermal Turbulence Detection in Infrared Imagery using YOLO
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Thermal turbulence degrades imaging performance in long-range infrared systems by introducing spatially varying distortions that appear as irregular intensity fluctuations and curvilinear patterns. Detecting these regions is challenging due to the absence of well-defined boundaries and their diffuse nature. This work investigates how structural characteristics of thermal turbulence influence automated detection using deep learning–based object detectors. A systematic study is conducted to evaluate different structural representations derived from thermal imagery, including rolling guidance filter (RGF), variance-based fluctuation maps, curvature-based features from the Hessian matrix, and multi-scale vesselness responses using the Frangi filter. These descriptors are incorporated as multi-channel inputs within a YOLO-based detection framework and evaluated on annotated infrared turbulence data. Results show that while deep detectors can capture turbulence cues from raw thermal images, structural representations improve the visibility of distortions and enhance detection robustness. In addition, intensity-based enhancement strategies are analysed to examine whether simple contrast amplification alone can improve turbulence detection performance. A structural fusion of thermal intensity and complementary feature representations achieves the best overall performance, improving localisation accuracy and recall. The findings highlight the importance of representation design in detecting diffuse thermal patterns and provide a more reliable framework for turbulence-aware detection in infrared imagery.
How to Cite
##plugins.themes.bootstrap3.article.details##
Thermal Turbulence Detection, Infrared Thermography, Structural Representation Learning, YOLOv11, Wind Turbine Monitoring
Bagavathiappan, S., Lahiri, B. B., Saravanan, T., Philip, J., & Jayakumar, T. (2013). Infrared thermography for condition monitoring: A review. Infrared Physics & Technology, 60, 35–55.
Banks, D. (2000). Visualization of in-flight flow phenomena using infrared thermography. NASA Dryden Flight Research Center.
Carlomagno, G. M., & Cardone, G. (2010). Infrared thermography for convective heat transfer measurements. Experiments in Fluids, 49(6), 1187–1218.
Chaudhuri, S., Stamm, M., Lapšanská, I., Lançon, T., Osterbrink, L., Driebe, T., ... Harendt, R. (2025). Infrared thermography of turbulence patterns of operational wind turbine rotor blades supported with high-resolution photography: KI-VISIR dataset. Wind Energy, 28(1), e2958.
Davis, W., & Atkins, N. R. (2024). Infrared thermography techniques for boundary layer state visualisation. Experiments in Fluids, 65(6), 91.
Ekici, S., Uyar, M., & Karadeniz, T. N. (2025). A-BiYOLOv9: An attention-guided YOLOv9 model for infrared-based wind turbine inspection. Applied Sciences, 15(21), 11840.
Feldmann, D., Oehme, F., von Germersheim, L., López Parras, R., Fischer, A., & Avila, M. (2022). Towards indirect assessment of surface anomalies on wind turbine rotor blades. In STAB/DGLR Symposium (pp. 529–538).
Fokaides, P. A., & Kalogirou, S. A. (2011). Application of infrared thermography for the determination of the overall heat transfer coefficient (U-value) in building envelopes. Applied Energy, 88(12), 4358–4365.
Frangi, A. F., Niessen, W. J., Vincken, K. L., & Viergever, M. A. (1998). Multiscale vessel enhancement filtering. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 130–137).
Haralick, R. M., Shanmugam, K., & Dinstein, I. H. (2007). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 6, 610–621.
Incropera, F. P. (2007). Fundamentals of heat and mass transfer. John Wiley.
Kumar, R., Sen, S., & Keprate, A. (2025). Real-time fatigue assessment of floating offshore wind turbine mooring employing sequence-to-sequence-based deep learning on indirect fatigue response. Ocean Engineering, 315, 119741. doi: https://doi.org/10.1016/j.oceaneng.2024.119741
Kumar, R., Sen, S., & Keprate, A. (2026). Fatigue damage assessment of FOWT mooring lines using sequence-to-sequence-based indirect sensing. In M. Singh et al. (Eds.), Proceedings of the Unified Conference of DAMAS, INCoME VIII and TEPEN Conferences (pp. 47–57). Cham: Springer Nature Switzerland.
Kumar, R., Thakur, A., Sen, S., & Keprate, A. (2026). Temporal feature extraction-based real-time damage detection of floating offshore wind turbine mooring lines. In M. Singh et al. (Eds.), Proceedings of the Unified Conference of DAMAS, INCoME VIII and TEPEN Conferences (pp. 59–68). Cham: Springer Nature Switzerland.
Lau, C. P., Lai, Y. H., & Lui, L. M. (2019). Restoration of atmospheric turbulence-distorted images via RPCA and quasiconformal maps. Inverse Problems, 35(7), 074002.
Lienhard, J. H. (2005). A heat transfer textbook. Phlogistron.
Oehme, F., Gleichauf, D., Suhr, J., Balaresque, N., Sorg, M., & Fischer, A. (2022). Thermographic detection of turbulent flow separation on rotor blades of wind turbines in operation. Journal of Wind Engineering and Industrial Aerodynamics, 226, 105025.
Raschka, S. (2014). About feature scaling and normalization and the effect of standardization for machine learning algorithms. Political Leg Anthropology Review, 30, 67–89.
Schwarzhans, F., George, G., Sanchez, L. E., Zaric, O., Abraham, J. E., Woitek, R., & Hatamikia, S. (2025). Image normalization techniques and their effect on the robustness and predictive power of breast MRI radiomics. European Journal of Radiology, 187, 112086.
Sirca Jr, G. F., & Adeli, H. (2018). Infrared thermography for detecting defects in concrete structures. Journal of Civil Engineering and Management, 24(7), 508–515.
Usamentiaga, R., Venegas, P., Guerediaga, J., Vega, L., Molleda, J., & Bulnes, F. G. (2014). Infrared thermography for temperature measurement and non-destructive testing. Sensors, 14(7), 12305–12348.
Uzun, E., & Akagündüz, E. (2025). Augmenting atmospheric turbulence effects on thermal-adapted deep object detection models. Scientific Reports, 15(1), 9900.
Watt, D., & McHugh, J. (1990). Infrared thermal imaging of atmospheric turbulence. In NASA Langley Research Center, Airborne Wind Shear Detection and Warning Systems: Second Combined Manufacturers’ and Technologists’ Conference, Part 1.
Yang, J., Ma, S., Sun, Q., Tan, W., Xu, M., Chen, N., & Zhao, D. (2014). Improved Hessian multiscale enhancement filter. Bio-Medical Materials and Engineering, 24(6), 3267–3275.
Yasarla, R., & Patel, V. M. (2020). Learning to restore a single face image degraded by atmospheric turbulence using CNNs. arXiv preprint arXiv:2007.08404.
Yasarla, R., & Patel, V. M. (2021). Learning to restore images degraded by atmospheric turbulence using uncertainty. In 2021 IEEE International Conference on Image Processing (ICIP) (pp. 1694–1698). doi: 10.1109/ICIP42928.2021.9506614
Zhang, Q., Shen, X., Xu, L., & Jia, J. (2014). Rolling guidance filter. In European Conference on Computer Vision (pp. 815–830).
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.