Enhancing Images in Poor Lighting Conditions Through Fusion of Optical and Thermal Camera Data

2025;
: pp. 229 - 232
1
Dnipro University of Technology, Ukraine
2
Dnipro University of Technology, Ukraine

The goal of the article is to provide a methodology of improving images quality in low-light conditions trough fusion of data received from telecamera and thermal camera. Data from thermal camera uses for compensation of significant illumination reduction in poor lighting conditions and allow keep required level of information. Proposed method establishes dynamic regulation of fusion coefficients depending on brightness level to minimize artifacts, increase edge sharpness, and improve object detectability. Developed model enables investigation of the influence of algorithmic parameters on key quality indicators, particularly PSNR, SSIM and target detection metrics. It has been shown that implementation of adaptive multimodal fusion principles ensures an increase in structural similarity by 15-20% and improvement in target detection accuracy in dark scenes by over 25% compared to using individual channels.

[1]    Wang,  M.,  Xu,  Z.,  Xu,  M.,  &  Lin,  W.  (2025).  Blind multimodal quality assessment of low-light images. International Journal of Computer Vision, 133(4), 1665- 1688. DOI: https://doi.org/10.1007/s11263-024-02239-9

[2]     Wang, Z., Li, D., Li, G., Zhang, Z., & Jiang, R. (2024). Multimodal low-light image enhancement with depth information. Proceedings of the 32nd ACM International Conference on Multimedia (pp. 4976-4985). DOI: https://doi.org/10.1145/3664647.3680741

[3]     Wu, Y., Cui, J., Niu, K., Lu, Y., Cheng, L., Cai, S., & Xu, C. (2025). RMF‐ED: Real‐Time Multimodal Fusion for Enhanced Target  Detection  in  Low‐Light Environments. IET CyberSystems and Robotics, 7(1), e70011. DOI: https://doi.org/10.1049/csy2.70011

[4]     Li, G., Ren, G., Wang, J., Zhi, M., Yu, Z., Jiang, B., ... &Guo, Q. (2025). Multimodal fusion transformer network for multispectral pedestrian detection in  low-light condition. Scientific Reports, 15(1), 18778. DOI: https://doi.org/10.1038/s41598-025-03567-7

[5]     Lei, X., Liu, L., Jia, P., Li, H., & Zhang, H. (2024). Low-Light Infrared and Visible Image Fusion with Imbalanced Thermal Radiation Distribution. IEEE Transactions on Instrumentation                                             and                    Measurement. DOI: 10.1109/TIM.2024.3453328.

[6]     Thaker, K., Chennupati, S., Rawashdeh, N., & Rawashdeh, S. A. (2023). Multispectral deep neural network fusion method for low-light  object  detection. Journal  of Imaging, 10(1), 12. DOI: https://doi.org/10.3390/ jimaging10010012

[7] Xu, J., Liao, M., Kathirvel, R. P., & Patel, V. M. (2024, September). Leveraging thermal modality to enhance reconstruction in low-light conditions. In European Conference on Computer Vision (pp. 321-339). Cham: Springer Nature Switzerland. DOI: https://doi.org/ 10.1007/978-3-031-72913-3_18

[8]     Sun, C., Wang, X., Fan, S., Dai, X., Wan, Y., Jiang, X., ...& Zhong, Y. (2025). NOT-156: Night Object Tracking using Low-light and Thermal Infrared: From Multi-modal Common-aperture Camera to Benchmark Datasets. IEEE Transactions   on    Geoscience   and   Remote    Sensing.DOI: 10.1109/TGRS.2025.3553695

[9]     Wang, Z., Wu, Y., Li, D., Tan, S., & Yin, Z. (2025, April). Thermal-Aware Low-Light Image Enhancement: A Real- World  Benchmark  and  a  New  Light-Weight  Model. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 8, pp. 8223-8231). DOI: https://doi.org/10.1609/aaai.v39i8.32887

[10] Sharma, S., Rani, S., Sharma, A., & Dogra, A. (2024, September). Enhancing Low-Light Vision through Infrared and Visible Image Fusion. In 2024 3rd International Conference for Advancement in Technology  (ICONAT) (pp. 1-7). DOI: https://doi.org/10.1109/ICONAT 61936.2024.10775080.

[11] Hnatushenko, V., Shedlovska, Y., & Shedlovsky, I. (2022, May). Processing technology of thematic identification and classification of objects in the multispectral remote sensing imagery. In International Scientific Conference “Intellectual Systems of Decision Making and Problem of Computational Intelligence”, (pp. 407-425). DOI: https://doi.org/10.1007/978-3-031-16203-9_24

[12] Kashtan, V., & Hnatushenko, V. V. (2020, June). A Wavelet and HSV Pansharpening Technology of High Resolution Satellite Images. In IntelITSIS (pp. 67-76).

[13] Hnatushenko, V., Nikulin, S., Kashtan, V., Korobko, O. (2024) Intelligent sentinel satellite image processing technology for land cover mapping, CEUR Workshop Proceedings, Volume: 3790, (pp. 194-203), DOI: https://doi.org/10.33271/nvngu/2024-5/143

[14] Kashtan, V., & Hnatushenko, V. (2022, May). Deep learning technology for automatic burned area extraction using satellite high spatial resolution images. In International Scientific  Conference “Intellectual  Systems of Decision Making  and Problem of Computational Intelligence”               (pp.              664-685).              DOI: https://doi.org/10.1007/978-3-031-16203-9_37