نوع مقاله : مقالة‌ تحقیقی‌ (پژوهشی‌)

نویسندگان

1 گروه ژئودزی و مهندسی نقشه برداری، دانشگاه تفرش، تفرش، ایران

2 استادیار، گروه ژئودزی و مهندسی نقشه برداری دانشگاه تفرش، تفرش، ایران

3 استادیار گروه ژئودزی و مهندسی نقشه برداری دانشگاه تقرش، تفرش، ایران

چکیده

تلفیق تصویر راهکاری رایج به‌منظور ایجاد هم‌افزایی در محتوای تصاویر چندطیفی و پانکروماتیک محسوب می‌شود. تاکنون راهکارهای مختلفی به‌منظور انجام فرایند تلفیق توسعه یافته‌اند که به‌کارگیری فضای فرکانس یکی از این راهکارها بشمار می‌رود. تلفیق تصاویر در فضای فرکانس به کمک فیلترهای بالاگذر و پایین گذر انجام شده که تعیین ابعاد بهینه‌ی فیلترها مهم‌ترین چالش آن محسوب می‌شود. در این مقاله به‌منظور بهره‌مندی توأمان از محتوای طیفی و جزئیات مکانی تصاویر، شاخصی وزن‌دار متشکل از دو شاخص رنگ‌پذیری و جزئیات مکانی پیشنهاد شده است. شاخص مذکور توانسته با اتکا به معیارهای هندسی و آماری فضای ویژگی در کنار به‌کارگیری فیلترهای نرم، نتایج مطلوبی را در شناسایی ابعاد بهینه‌ی فیلترگذاری تأمین سازد. در سازوکار پیشنهادی، وزن شاخص‌های رنگ‌پذیری و جزئیات مکانی با در نظر گرفتن تمایز در محتوای تصاویر، برای هر تصویر به‌طور مستقل برآورد می‌گردد. مقایسه‌ی بهترین نتایج کسب‌شده از روش پیشنهادی با روش‌های رایج تلفیق حاکی از بهبود به‌طور متوسط 58 درصدی در دقت (RMSE) فرایند تلفیق می‌باشد.

کلیدواژه‌ها

عنوان مقاله [English]

A method for determining the optimum parameter of the soft filters to image fusion in the frequency domain

نویسندگان [English]

  • Kobra Yaghoubi 1
  • Alireza Safdarinezhad 2
  • Marzieh Jafari 3

1 Department of Geodesy and Surveying Engineering. Tafrsh University. Tafresh. Iran

2 Department of Geodesy and Surveying Engineering, Tafresh University, Tafresh. Iran

3 Department of Geodesy and Surveying Engineering.Tafresh University. Tafresh, Iran

چکیده [English]

Image fusion is known as a synergetic process for merging multispectral and panchromatic images contents. So far, various methods have been developed in which the usage of the frequency domain is one of them. The frequency-based image fusion techniques are performed using high and low pass filters. So, the determination of the sizes of these filters would be a challenge. In this paper, a weighted index is proposed to determine the sizes and shapes of the low and high filters in fusion of the panchromatic and multispectral images. In the proposed method, the weights of the spectral and spatial indicators are independently estimated for each image. So, the effects of the differentiation of the image contents and different range of the indicators are properly adjusted to reach the optimum filtering. The comparison of the best results obtained from the proposed method with the other well-known fusion methods, in the used datasets, was indicated an average improvement of 58% in RMSEs.

کلیدواژه‌ها [English]

  • Remote Sensing
  • Image fusion
  • Frequency Domain
  • Fast Fourier Transform
  • Filtering
  1. Ma, H. Wu, L. Wang, B. Huang, R. Ranjan, A. Zomaya, et al., "Remote sensing big data computing: Challenges and opportunities," Future Generation Computer Systems, vol. 51, pp. 47-60, 2015.
  2. Zhang, F. Zhang, and S. Yang, "Fusion of multispectral and panchromatic images via spatial weighted neighbor embedding," Remote Sensing, vol. 11, p. 557, 2019.
  3. Hellweger, P. Schlosser, U. Lall, and J. Weissel, "Use of satellite imagery for water quality studies in New York Harbor," Estuarine, Coastal and Shelf Science, vol. 61, pp. 437-448, 2004
  4. Kaur and J. Kaur, "Comparison of image fusion techniques: spatial and transform domain based techniques," International Journal of Engineering And Computer Science, vol. 4, pp. 12109-12112, 2015.
  5. Manchanda, "Fusion of Multispectral and Panchromatic Images based on Fourier Filtering in HSV Color Space." International Journal of Trend in Scientific Research and Development, vol.1, no.4, pp.632-635, 2017
  6. Li, L. Jing, Y.Tang, and L. Wang, “An image Fusion method based on image segmentation for high-resolution remotely-sensed imagery,” Remote Sensing, vol.10, no.5, pp.790, 2018
  7. Ling, M. Ehlers, E.L. Usery and M. Madden, “FFT-enhanced IHS transform method for fusing high-resolution satellite images,” ISPRS Journal of photogrammetry and Remote Sensing, vol. 61, no.6, pp.381-392, 2018
  8. Denipote, J.G. and Paiva, M.S.V., “A Fourier transform-based approach to fusion high spatial resolution remote sensing images,”Sixth Indian Conference on Computer Vision, Graphics & Image Processing, IEEE,179-186, 2008
  9. Safdarinezhad, A. Rahmanizadeh, , M. Valadan Zoej, M. Mokhtarzade and M. Jannati, “Robust method for ikonos imagery fusion in frequency domain,” International Conference on Advancements in Electronics and Power Engineering, pp.103-108, 2011.
  10. Hu, B. Xiangli, L. Su and Y. Yuan, “Fusion of multispectral and panchromatic images using lab transform based on Fourier filtering,” International Geoscience and Remote Sensing Symposium, IEEE, pp.3384-2287, 2012.
  11. Bashiropur, M. Valadan Zoej and Y. Maqsoudi, “FFT-PCA method for fusing remote sensing imagery,” Engineering Journal of Geospatial Information Technology, vol.5, no.2, pp.123-140, 2017, (in persian).
  12. P.S. Naidu, “Multi-resolution image fusion by FFT,” International Conference on Image Information Processing, IEEE, pp.1-6, 2011.
  13. G. Kumar, S.K. Sahoo, and P.K. Meher, “50 years of fft algorithms and applications,”Circuits, Systems, and Signal Processing, pp.1-34, 2019.
  14. S. Shaikh, A. Choudhry and R. Wadhwani, “Analysis of digital image filters in frequency domain,”  International Journal of Computer Applications, vol.140, no. 6, pp.12-19, 2016.
  15. Sonnad, “A survey on fusion of multi spectral and panchromatic images for high spatial and spectral information,” In 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) IEEE, pp.177-180, 2016.
  16. Trstenjak, S. Mikac and J. Trstenjak, “The framework for fast skew angle detectionand auto correction of scanned  documents,” Annals of DAAAM & Proceedings vol. 29,  pp.0486-494, 2018.
  17. Garzelli, F. Nencini and L. Capobianco, “Optimal MMSE pan sharpening of very high resolution multispectral images,” IEEE Transactions on Geoscience and Remote Sensing, vol. 46, no. 1, pp. 228-236, 2008.
  18. Zhong, B. Yang, G. Huang, F. Zhong and Z. Chen, “Remote sensing image fusion with convolutional neural network, ” Sensing and Imaging, vol.17, no.1, p.10, 2016.
  19. Jagalingam and A.V. Hegde, “A review of quality metrics for fused image,” International Conference on Water Resources, Costal and Ocean Engineering (ICWRCOE), pp.133-142, 2015.
  20. Boztoprak, “An alternative image quality assessment method for blurred images,” Balkan Journal of Electrical and Computer Engineering, vol. 4, no.1, , pp.46-50, 2016.
  21. A. Al-Wassai, N.V. Kalyankar, “A novel metric approach evaluation for the spatial enhancement of pansharpened images,” arXiv preprint arXiv: 1207.5064, 2012.
  22. Pohl and J. Van Genderen, Remote Sensing Image Fusion: A Practical Guide, Crc Press, p.158-159, 2016.
  23. Pistonesi, J.Martinez, S. Ojeda and R.Vallejos, “Structural similarity metrics for quality image fusion assessment: Algorithms,”Image Processing on Line, pp. 345-368, 2018.
  24. Alparone, B. Aiazzi, S. Baronti and A. Garzelli, Remote sensing image fusion, ser. Signal and Image Processing of Earth Observations. Boca Raton, FL: CRC Press, 2015.
  25. Dou, “Image degradation for quality assessment of pan-sharpening methods,”Remote Sensing, vol.10, no.1, p. 154, 2018.
  26. Makandar and B. Halalli, “Image enhancement techniques using highpass and lowpass filters,” International Journal of Computer Applications, vol.109, no.14, pp.12-15, 2015.
  27. Dogra and D. Ayush, “Performance comparison of gaussian and elliptic high pass filter,” International Journal of Advanced Biological and Biomedical Research, Vol. 3, No.1, pp. 93-96, 2015.
  28. Patanavijit, “performance analysis of digital fir lp filter implementation based on 5 window techniques: rectangular, barlett, hann, hamming and blackman,” International Journal of Simulation-Systems, Science & Technology, Vol. 20, No. 3, pp.11.1-11.6, 2019.
  29. Jadhav, “image fusion based on wavelet transform,” International Journal of Engineering Research, vol.3, no.7, pp.442-445, 2014.
  30. R. Pandit and R. J. Bhiwani, “Image fusion in remote sensing applications: A review,” International journal of computer applications,vol.120, no.10, pp. 22-32, 2015.
  31. Welch and W, Ahlers, “Merging multiresolution SPOT HRV and Landsat TM data,” Photogrammetric Engineering & Remote Sensing, vol.53, no.3, pp.301-303, 1987.
  32. J. Vrabel, P. Doraiswamy and A. Stern, “Application of hyperspectral imagery resolution improvement for site-specific farming,” In ASPRS 2002 Conference Proceedings, 2002.