KaydedilenlerDerginizi ekleyin

Dergiler / Türkiye Uzaktan Algılama Dergisi / 2026 / Volume: 8

Modified very deep super resolution network - Gaussian mixture models based single image super-resolution: A comprehensive comparative analysis

Mehmet Akıf Günen(GÜMÜŞHANE ÜNİVERSİTESİ, GÜMÜŞHANE MÜHENDİSLİK FAKÜLTESİ)0000-0001-5164-375X
Sayfa
—
Yayın Tarihi
2026-07-03
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

The proposed mVDSR-GMM emerges as a promising tool for advancing satellite imagery resolution, with potential applications in remote sensing and geospatial analysis.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Image Super-Resolution (SISR) is a vital, cost-effective solution for enhancing the spatial resolution of satellite imagery.
📊
Temel Bulgular & Veri:However, a significant challenge in current SISR techniques is that while deep learning models excel at structural learning, they often struggle to accurately reconstruct intricate high-frequency details and preserve the statistical texture properties of high-resolution images.
💡
Sonuç & Katkı:The proposed mVDSR-GMM emerges as a promising tool for advancing satellite imagery resolution, with potential applications in remote sensing and geospatial analysis.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:Single image super-resolution · Satellite imagery · Gaussian mixture models

Abstract

Image Super-Resolution (SISR) is a vital, cost-effective solution for enhancing the spatial resolution of satellite imagery. However, a significant challenge in current SISR techniques is that while deep learning models excel at structural learning, they often struggle to accurately reconstruct intricate high-frequency details and preserve the statistical texture properties of high-resolution images. To address this gap, this paper proposes a novel hybrid method, termed mVDSR-GMM, which leverages the complementary strengths of Gaussian Mixture Models (GMM) and a modified Very Deep Super-Resolution (mVDSR) network. GMM is utilized to model the underlying statistical and probabilistic properties of the image for accurate high-frequency reconstruction while the mVDSR network enhanced with 25 convolutional layers and Leaky ReLU activations boosts the model’s structural feature extraction and non-linear mapping capabilities. This hybrid approach technically integrates the mVDSR and GMM through a parallel merging of their estimated residuals within the luminance channel, thereby enhancing the spatial reconstruction of satellite imagery. The enhanced mVDSR network, with increased depth and Leaky ReLU activation functions, further boosts the model's learning capability and robustness. Through extensive evaluations using satellite imagery datasets and metrics such as PSNR, SSIM, BRISQUE, MSE, UIQI, SAM, and FD, mVDSR-GMM consistently outperformed existing techniques, demonstrating its effectiveness in improving spatial resolution. Experimental results indicate that mVDSR-GMM outperforms main competitors such as SwinIR and SinSR across all evaluation metrics, providing a robust reconstruction performance that is further validated by improved accuracy in the binary separation of urban structures (buildings and roads) from natural environments. The proposed mVDSR-GMM emerges as a promising tool for advancing satellite imagery resolution, with potential applications in remote sensing and geospatial analysis.

🔖

Bu Makaleye Atıf Yap

Günen, M. A. (2026). Modified very deep super resolution network - Gaussian mixture models based single image super-resolution: A comprehensive comparative analysis. Türkiye Uzaktan Algılama Dergisi, Volume: 8. https://doi.org/10.51489/tuzal.1829904

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (52)

  1. Agustsson, E., & Timofte, R. (2017). Ntire 2017 challenge on single image super-resolution: Dataset and study. Proceedings Book of the IEEE conference on computer vision and pattern recognition workshops, Honolulu, Hawaii, USA. 126-135.
  2. Al-Mekhlafi, H., & Liu, S. (2024). Single image super-resolution: A comprehensive review and recent insight. Frontiers of Computer Science, 18, 181702. https://doi.org/10.1007/s11704-023-2588-9
  3. Arabi Aliabad, F., Ghafarian Malmiri, H., Sarsangi, A., Sekertekin, A., & Ghaderpour, E. (2023). Identifying and monitoring gardens in urban areas using aerial and satellite imagery. Remote Sensing, 15(16), 4053. https://doi.org/10.3390/rs15164053
  4. Atasever, U. H., & Günen, M. A. (2021). Change detection approach for SAR imagery based on arc-tangential difference image and k-Means++. IEEE Geoscience and Remote Sensing Letters, 19, 1–5. https://doi.org/10.1109/LGRS.2021.3127964
  5. Ayala, C., Sesma, R., Aranda, C., & Galar, M. (2021). A deep learning approach to an enhanced building footprint and road detection in high-resolution satellite imagery. Remote Sensing, 13(16), 3135. https://doi.org/10.3390/rs13163135
  6. Chen, C., & Fowler, J. E. (2012). Single-image super-resolution using multihypothesis prediction. Forty Sixth Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA, 608–612.
  7. Chen, Y.-K., Cheng, F.-C., & Tsai, P. (2011). A gray-level clustering reduction algorithm with the least PSNR. Expert Systems with Applications, 38(8), 10183–10187. https://doi.org/10.1016/j.eswa.2011.02.071
  8. Chen, Y., Liu, L., Phonevilay, V., Gu, K., Xia, R., Xie, J., Zhang, Q., & Yang, K. (2021). Image super-resolution reconstruction based on feature map attention mechanism. Applied Intelligence, 51, 4367–4380. https://doi.org/10.1007/s10489-020-02116-1
  9. Cheng, M., Ma, H., Ma, Q., Sun, X., Li, W., Zhang, Z., Sheng, X., Zhao, S., Li, J., & Zhang, L. (2023). Hybrid transformer and CNN attention network for stereo image super-resolution. Proceedings Book of IEEE Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, 1702–1711.
  10. Civicioglu, P., & Besdok, E. (2022). Contrast stretching based pansharpening by using weighted differential evolution algorithm. Expert Systems with Applications, 208, 118144. https://doi.org/10.1016/j.eswa.2022.118144
  11. Civicioglu, P., & Besdok, E. (2024). Pansharpening of remote sensing images using dominant pixels. Expert Systems with Applications, 242, 122783. https://doi.org/10.1016/j.eswa.2023.122783
  12. Courtrai, L., Pham, M.-T., & Lefèvre, S. (2020). Small object detection in remote sensing images based on super-resolution with auxiliary generative adversarial networks. Remote Sensing, 12(19), 3152. https://doi.org/10.3390/rs12193152
  13. Dabbech, A., Terris, M., Jackson, A., Ramatsoku, M., Smirnov, O. M., & Wiaux, Y. (2022). First AI for deep super-resolution wide-field imaging in radio astronomy: Unveiling structure in ESO 137-006. The Astrophysical Journal Letters, 939, L4. https://doi.org/10.3847/2041-8213/ac98af
  14. Dai, Q., Cheng, X., Qiao, Y., & Zhang, Y. (2020). Crop leaf disease image super-resolution and identification with dual attention and topology fusion generative adversarial network. IEEE Access, 8, 55724–55735. https://doi.org/10.1109/ACCESS.2020.2982055
  15. Dong, C., Loy, C. C., He, K., & Tang, X. (2014). Learning a deep convolutional network for image super-resolution. European Conference on Computer Vision. Springer.
  16. Dornaika, F., Moujahid, A., El Merabet, Y., & Ruichek, Y. (2016). Building detection from orthophotos using a machine learning approach: An empirical study on image segmentation and descriptors. Expert Systems with Applications, 58, 130–142. https://doi.org/10.1016/j.eswa.2016.03.024
  17. Fan, Y., Ding, X., Wu, J., Ge, J., & Li, Y. (2021). High spatial-resolution classification of urban surfaces using a deep learning method. Building and Environment, 200, 107949. https://doi.org/10.1016/j.buildenv.2021.107949
  18. Farooq, M., Dailey, M. N., Mahmood, A., Moonrinta, J., & Ekpanyapong, M. (2021). Human face super-resolution on poor quality surveillance video footage. Neural Computing and Applications, 33, 13505–13523. https://doi.org/10.1007/s00521-021-05973-0
  19. Glasner, D., Bagon, S., & Irani, M. (2009). Super-resolution from a single image. IEEE Conference on Computer Vision and Pattern Recognition. Springer.
  20. Grinias, I., Panagiotakis, C., & Tziritas, G. (2016). MRF-based segmentation and unsupervised classification for building and road detection in peri-urban areas of high-resolution satellite images. ISPRS Journal of Photogrammetry and Remote Sensing, 122, 145–166. https://doi.org/10.1016/j.isprsjprs.2016.10.010
  21. Günen, M. A. (2021). Weighted differential evolution algorithm based pansharpening. International Journal of Remote Sensing, 42(21), 8468–8491. https://doi.org/10.1080/01431161.2021.1976874
  22. Günen, M. A. (2022). Performance comparison of deep learning and machine learning methods in determining wetland water areas using EuroSAT dataset. Environmental Science and Pollution Research, 29, 21092–21106. https://doi.org/10.1007/s11356-021-17177-z
  23. Günen, M. A. (2023). Comparison of histogram-curve fitting-based and global threshold methods for cloud detection. International Journal of Environmental Science and Technology, 1–26. https://doi.org/10.1007/s13762-023-05379-6
  24. Günen, M. A., Pérez-Delgado, M.-L., & Beşdok, E. (2024). L0-Norm based image pansharpening by using population-based algorithms. AIMS Mathematics, 9(1), 32578–32628. https://doi.org/10.3934/math.20241561
  25. He, J., Yuan, Q., Li, J., Xiao, Y., Liu, D., Shen, H., & Zhang, L. (2023). Spectral super-resolution meets deep learning: Achievements and challenges. Information Fusion, 101, 101812. https://doi.org/10.1016/j.inffus.2023.101812
  26. Jiang, J., Wang, C., Liu, X., & Ma, J. (2021). Deep learning-based face super-resolution: A survey. ACM Computing Surveys, 55(1), 1–36. https://doi.org/10.1145/3485132
  27. Joshi, O., Joshi, A., & Sawant, S. (2022). 2D MRI super resolution using generative adversarial network. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4291804
  28. Kim, J., Lee, J. K., & Lee, K. M. (2016). Accurate image super-resolution using very deep convolutional networks. Proceedings Book of the IEEE conference on computer vision and pattern recognition, Las Vegas, Nevada, USA, 1646-1654.
  29. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., & Shi, W. (2017). Photo-realistic single image super-resolution using a generative adversarial network. Proceedings Book of the IEEE conference on computer vision and pattern recognition, Honolulu, Hawaii, USA, 4681-4690.
  30. Lei, S., Shi, Z., & Mo, W. (2021). Transformer-based multistage enhancement for remote sensing image super-resolution. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–11. https://doi.org/10.1109/TGRS.2021.3136190
  31. Leinonen, J., Nerini, D., & Berne, A. (2020). Stochastic super-resolution for downscaling time-evolving atmospheric fields with a generative adversarial network. IEEE Transactions on Geoscience and Remote Sensing, 59(9), 7211–7223. https://doi.org/10.1109/TGRS.2020.3032790
  32. Lepcha, D. C., Goyal, B., Dogra, A., & Goyal, V. (2023). Image super-resolution: A comprehensive review, recent trends, challenges and applications. Information Fusion, 91, 230–260. https://doi.org/10.1016/j.inffus.2022.10.007
  33. Misra, M., Kumar, D., & Shekhar, S. (2020). Assessing machine learning based supervised classifiers for built-up impervious surface area extraction from Sentinel-2 images. Urban Forestry & Urban Greening, 53, 126714. https://doi.org/10.1016/j.ufug.2020.126714
  34. Mittal, A., Moorthy, A. K., & Bovik, A. C. (2011). Blind/referenceless image spatial quality evaluator. Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA, 723–727. https://doi.org/10.1109/ACSSC.2011.6190099
  35. Ogawa, Y., Ariki, Y., & Takiguchi, T. (2012a). Super-resolution by GMM based conversion using self-reduction image. IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, Japan, 2012, 1285–1288. https://doi.org/10.1109/ICASSP.2012.6288124
  36. Ogawa, Y., Hori, T., Takiguchi, T., & Ariki, Y. (2012b). Super-resolution using GMM and PLS regression. IEEE International Symposium on Multimedia, Irvine, CA, USA, 298–301. https://doi.org/10.1109/ISM.2012.62
  37. Ok, A. O. (2013). Automated detection of buildings from single VHR multispectral images using shadow information and graph cuts. ISPRS Journal of Photogrammetry and Remote Sensing, 86, 21–40. https://doi.org/10.1016/j.isprsjprs.2013.09.004
  38. Özyurt, F., Sert, E., & Avcı, D. (2020). An expert system for brain tumor detection: Fuzzy C-means with super resolution and convolutional neural network with extreme learning machine. Medical Hypotheses, 134, 109433. https://doi.org/10.1016/j.mehy.2019.109433
  39. Pérez-Delgado, M.-L., & Günen, M. A. (2023). A comparative study of evolutionary computation and swarm-based methods applied to color quantization. Expert Systems with Applications, 224, 120666. https://doi.org/10.1016/j.eswa.2023.120666
  40. Ran, Q., Xu, X., Zhao, S., Li, W., & Du, Q. (2020). Remote sensing images super-resolution with deep convolution networks. Multimedia Tools and Applications, 79, 8985–9001. https://doi.org/10.1007/s11042-018-7091-1
  41. Salguero-Cruz, A., Latorre-Carmona, P., & García-Osorio, C. I. (2022). Proposal of a comparative framework for face super-resolution algorithms in forensics. Iberian Conference on Pattern Recognition and Image Analysis. Springer.
  42. Sandeep, P., & Jacob, T. (2016). Single image super-resolution using a joint GMM method. IEEE Transactions on Image Processing, 25(9), 4233–4244. https://doi.org/10.1109/TIP.2016.2588319
  43. Sheikh, M. A. A., Maity, T., & Kole, A. (2022). Man-made object extraction from remote sensing images using Gabor energy features and probabilistic neural networks. ICTACT Journal on Image & Video Processing, 13(1). https://doi.org/10.21917/ijivp.2022.0407
  44. Singh, A., & Singh, J. (2020). Survey on single image based super-resolution—implementation challenges and solutions. Multimedia Tools and Applications, 79, 1641–16472. https://doi.org/10.1007/s11042-019-08254-0
  45. Şan, M., Akpınar, A., Bingölbali, B., & Kankal, M. (2021). Geo-spatial multi-criteria evaluation of wave energy exploitation in a semi-enclosed sea. Energy, 214, 118997. https://doi.org/10.1016/j.energy.2020.118997
  46. Tai, Y., Yang, J., & Liu, X. (2017). Image super-resolution via deep recursive residual network. Proceedings Book of the IEEE conference on computer vision and pattern recognition workshops, Honolulu, Hawaii, USA, 3147–3155.
  47. Ünsalan, C., & Boyer, K. L. (2005). A system to detect houses and residential street networks in multispectral satellite images. Computer Vision and Image Understanding, 98(3), 423–461. https://doi.org/10.1016/j.cviu.2004.10.006
  48. Wang, P., Bayram, B., & Sertel, E. (2022a). A comprehensive review on deep learning based remote sensing image super-resolution methods. Earth-Science Reviews, 232, 104110. https://doi.org/10.1016/j.earscirev.2022.104110
  49. Wang, Y., Bashir, S. M. A., Khan, M., Ullah, Q., Wang, R., Song, Y., Guo, Z., & Niu, Y. (2022b). Remote sensing image super-resolution and object detection: Benchmark and state of the art. Expert Systems with Applications, 197, 116793. https://doi.org/10.1016/j.eswa.2022.116793
  50. 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. https://doi.org/10.1109/TIP.2003.819861
  51. Yang, J., Wright, J., Huang, T. S., & Ma, Y. (2010). Image super-resolution via sparse representation. IEEE Transactions on Image Processing, 19(11), 2861–2873. https://doi.org/10.1109/TIP.2010.2050625
  52. Zhang, Y., Tian, Y., Kong, Y., Zhong, B., & Fu, Y. (2018). Residual dense network for image super-resolution. Proceedings Book of the IEEE conference on computer vision and pattern recognition, Salt Lake City, Utah, USA, 2472–2481.