SavedAdd your journal

Journals / Türk Deprem Araştırma Dergisi / 2026 / Cilt: 7 Sayı: 1

Enhancing the Quality of Satellite Images in Disaster Management: A Comparative Analysis of Zero-DCE, CIDNet, and MIRNet Models

Doğal Afet Yönetiminde Uydu Görüntülerinin Kalitesinin İyileştirilmesi: Zero-DCE, CIDNet ve MIRNet Modellerinin Karşılaştırmalı Analizi

Mehmet Umut Salur(Gaziantep İslam Bilim ve Teknoloji Üniversitesi)0000-0003-0296-6266
Çağrı Karakaş(FIRAT ÜNİVERSİTESİ)0009-0001-9196-4387
İlhan Aydın(FIRAT ÜNİVERSİTESİ)0000-0001-6880-4935
Pages
101–114
Publication Date
2025-04-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results showed that CIDNet was superior in detail and structural accuracy, while MIRNet was successful in color and brightness enhancement.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Satellite images play a critical role in disaster management and rescue operations in natural disasters.
📊
Key Findings & Data:This study evaluates the performance of deep learning models—Zero-DCE, CIDNet, and MIRNet—in enhancing low-light satellite images.
💡
Conclusion & Impact:The results showed that CIDNet was superior in detail and structural accuracy, while MIRNet was successful in color and brightness enhancement.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Düşük ışık görüntü iyileştirme · Derin öğrenme · Zero-DCE

Abstract

Satellite images play a critical role in disaster management and rescue operations in natural disasters. However, these images create difficulties in analysis due to noise and loss of detail. This study evaluates the performance of deep learning models—Zero-DCE, CIDNet, and MIRNet—in enhancing low-light satellite images. The performances of the models were analyzed with metrics such as PSNR, SSIM and LPIPS using post-earthquake satellite images of the Hatay region. In addition, the performance of the models on a benchmark dataset was analyzed. The results showed that CIDNet was superior in detail and structural accuracy, while MIRNet was successful in color and brightness enhancement. Although Zero-DCE was effective in brightness enhancement, it lagged behind other models in structural accuracy. In this study, the potential of deep learning-based image enhancement models in disaster management and the image features on which they are effective were revealed.

Özet

Doğal afetlerde uydu görüntüleri, afet yönetimi ve kurtarma operasyonlarında kritik bir rol oynamaktadır. Ancak düşük ışık koşullarında elde edilen bu görüntüler, gürültü ve detay kaybı nedeniyle analizlerde zorluk yaratmaktadır. Bu çalışmada, düşük ışık uydu görüntülerinin iyileştirilmesinde Zero-DCE, CIDNet ve MIRNet modellerinin performansları değerlendirilmiştir. Hatay bölgesine ait deprem sonrası uydu görüntüleri kullanılarak modellerin PSNR, SSIM ve LPIPS gibi metriklerle performansları analiz edilmiştir. Ayrıca modellerin bir kıyaslama veri kümesindeki başarımı da analiz edilmiştir. Sonuçlar, CIDNet’in detay ve yapısal doğrulukta üstün olduğunu, MIRNet’in ise renk ve parlaklık iyileştirme konusunda başarılı olduğunu göstermiştir. Zero-DCE, parlaklık artırmada etkili olsa da yapısal doğrulukta diğer modellere göre geride kalmıştır. Bu çalışmada derin öğrenme tabanlı görüntü iyileştirme modellerinin afet yönetimindeki kullanım potansiyeli ve etkili oldukları görüntü özellikleri ortaya konulmuştur.

🔖

Cite This Article

Salur, M. U., Karakaş, Ç., Aydın, İ. (2025). Enhancing the Quality of Satellite Images in Disaster Management: A Comparative Analysis of Zero-DCE, CIDNet, and MIRNet Models. Türk Deprem Araştırma Dergisi, Cilt: 7 Sayı: 1, 101–114. https://doi.org/10.46464/tdad.1600376

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (31)

  1. Anoop P.P., Deivanathan R., 2024. Advancements in low light image enhancement techniques and recent applications, Journal of Visual Communication and Image Representation, 104223.
  2. Avcibas I.S., Sankur B.L., Sayood K., 2002. Statistical evaluation of image quality measures, Journal of Electronic Imaging, 11(2), 206-223.
  3. Cadik M., Slavik P., 2004. Evaluation of two principal approaches to objective image quality assessment, Eighth International Conference on Information Visualisation, 16-16 July 2004, London, UK, Erişim adresi: https://doi.org/10.1109/IV.2004.1320193.
  4. Chinaramanamma D., Anuradha B., 2024. Image enhancement of satellite images using contrast limited adaptive histogram equalization and NLM, International Journal of Scientific Research in Science and Technology, 11(2), 177-181.
  5. Farrell J.E., 1999. Image quality evaluation, Colour imaging: vision and technology, 1(1), 285-313.
  6. Guo C., Li C., Guo J., Loy C.C., Hou J., Kwong S., Cong R., 2020. Zero-reference deep curve estimation for low-light image enhancement, IEEE/CVF conference on computer vision and pattern recognition, 13-19 June 2020, Seattle, WA, USA, Erişim adresi: https://doi.org/10.1109/CVPR42600.2020.00185.
  7. Hanis S., Narayanan S.A., Viswanath P.A., Bhooshan V., 2023. Satellite and Aerial Image Restoration Using Deep Reinforcement Learning, Fluctuation and Noise Letters, 22(05), 2350039.
  8. Hore A., Ziou D., 2010. Image quality metrics: PSNR vs. SSIM, 20th international conference on pattern recognition, 23-26 August 2010, Istanbul, Turkey, Erişim adresi: https://doi.org/10.1109/ICPR.2010.579.
  9. HVI-CIDNet GitHub repository, 2024. HVI-CIDNet: An Efficient Network for Low-light Image Enhancement, Erişim adresi: https://github.com/Fediory/HVI-CIDNet.
  10. Kim W., 2022. Low-light image enhancement: A comparative review and prospects, IEEE Access, 10, 84535-84557.
  11. Kreis R., 2004. Issues of spectral quality in clinical 1H‐magnetic resonance spectroscopy and a gallery of artifacts, NMR in Biomedicine, 17(6), 361-381.
  12. Lei C., Tian Q., 2023. Low-Light Image Enhancement Algorithm Based on Deep Learning and Retinex Theory, Applied Sciences, 13(18), 10336.
  13. Li C., Guo C., Han L., Jiang J., Cheng M.M., Gu J., Loy C.C., 2022. Low-light image and video enhancement using deep learning: A survey, IEEE transactions on pattern analysis and machine intelligence, 44(12), 9396-9416.
  14. Matsui T., Ikehara M., 2023. Low-light image enhancement using a simple network structure, IEEE Access, 11, 65507-65516.
  15. MIRNet GitHub repository, 2024. MIRNet: Learning Enriched Features for Real Image Restoration and Enhancement, Erişim adresi: https://github.com/swz30/MIRNet.
  16. Naik V.V., Gharge S., 2016. Satellite image resolution enhancement using DTCWT and DTCWT based fusion, International Conference on Advances in Computing, Communications and Informatics, 21-24 September 2016, Jaipur, India, Erişim adresi: https://doi.org/10.1109/ICACCI.2016.7732338.
  17. Pan X., Li C., Pan Z., Yan J., Tan S., Yin X., 2022. Low-light image enhancement method based on retinex theory by improving illumination map, Applied Sciences, 12(10), 5257.
  18. Park S., Kim K., Yu S., Paik J., 2018. Contrast enhancement for low-light image enhancement: A survey, IEIE Transactions on Smart Processing & Computing, 7(1), 36-48.
  19. Putri A., Hartono B., Ayu N., 2024. Image Processing Techniques for Enhancing Satellite Imagery in Disaster Management, International Journal of Computer Technology and Science, 1(1), 14-17.
  20. Sharma L., Sengupta S., Kumar B., 2021. An improved technique for enhancement of satellite image, Journal of physics: Conference series, 1714(1), 12051.
  21. Singh A., Chougule A., Narang P., Chamola V., Yu F.R., 2022. Low-light image enhancement for UAVs with multi-feature fusion deep neural networks, IEEE Geoscience and Remote Sensing Letters, 19, 1-5.
  22. Thriveni R., Ramashri, 2013. Satellite image enhancement using discrete wavelet transform and threshold decomposition driven morphological filter, 2013 International Conference on Computer Communication and Informatics, 4-6 January 2013, Coimbatore, INDIA, Erişim adresi: https://doi.org/10.1109/ICCCI.2013.6466114.
  23. Tian Z., Qu P., Li J., Sun Y., Li G., Liang Z., Zhang W., 2023. A survey of deep learning-based low-light image enhancement, Sensors, 23(18), 7763.
  24. Trung N.T., Le X.H., Tuan T.M., 2023. Enhancing contrast of dark satellite images based on fuzzy semi-supervised clustering and an enhancement operator, Remote Sensing, 15(6), 1645.
  25. Wang Z., Bovik A.C., Sheikh H.R., Simoncelli E.P., 2004. Image quality assessment: from error visibility to structural similarity, IEEE transactions on image processing, 13(4), 600-612.
  26. Wei C., Wang W., Yang W., Liu J., 2018. Deep retinex decomposition for low-light enhancement, arXiv preprint arXiv:1808.04560, Erişim adresi: https://arxiv.org/abs/1808.04560.
  27. Yan Q., Feng Y., Zhang C., Wang P., Wu P., Dong W., Zhang Y., 2024. You only need one color space: An efficient network for low-light image enhancement, arXiv preprint, Erişim adresi: https://arxiv.org/pdf/2402.05809.
  28. Yulang C., Jingmin G.A.O., Kebei Z., Yang Z., 2021. Low-light image enhancement of space satellites based on GAN, Chinese Space Science and Technology, 41(3), 16-23.
  29. Zamir S.W., Arora A., Khan S., Haya M., Khan F.S., Yang M.H., Shao L., 2020. Learning enriched features for real image restoration and enhancement, Computer Vision–ECCV 2020: 16th European Conference, 23–28 August 2020, Glasgow, UK, Erişim adresi: https://arxiv.org/pdf/2003.06792.
  30. Zero-DCE GitHub repository, 2024. Zero-DCE: Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement, Erişim adresi: https://github.com/Li-Chongyi/Zero-DCE.
  31. Zhang R., Isola P., Efros A.A., Shechtman E., Wang O., 2018. The unreasonable effectiveness of deep features as a perceptual metric, IEEE conference on computer vision and pattern recognition, 18-23 June 2018, Salt Lake City, UT, USA, Erişim adresi: https://doi.org/10.1109/CVPR.2018.00068.