Hiperspektral görüntülerin otomatik uyarlamalı ışıklılık dönüşümü ve 3D-DCT yöntemi kullanılarak sıkıştırılması

Yıl 2020, Cilt: 26 Sayı: 5, 868 - 883, 23.10.2020

Ergün Can Ali Can Karaca Oğuzhan Urhan Mehmet Kemal Güllü

Öz

Hiperspektral görüntüleme, farklı uygulama alanlarındaki kullanımı ile son yıllarda oldukça popüler bir konu haline gelmiştir. Yüksek depolama alanlarına ihtiyaç duyan hiperspektral görüntülerin yüksek verim ve kalite ile sıkıştırılması gerekmektedir. Bu çalışmada, hiperspektral görüntülerin kayıplı sıkıştırılması için otomatik uyarlamalı ışıklılık dönüşümü ve üç-boyutlu ayrık kosinüs dönüşümünü (3D-DCT) kullanan özgün bir yöntem önerilmektedir. Önerilen yöntemde ilk olarak hiperspektral verideki spektral bantlar gruplanmış ve ön işlem olarak otomatik uyarlamalı ışıklılık dönüşümü uygulanmıştır. Elde edilen her bant grubu ayrık kosinüs dönüşümü ve sonrasında Huffman kodlama kullanılarak sıkıştırılmıştır. Önerilen ışıklılık dönüşümünün amacı, bir grup içindeki bant imgeleri arasındaki ışıklılık ve karşıtlık farklılıklarını azaltarak sıkıştırma performansının arttırılmasını sağlamaktır. Deneysel sonuçlarda, Cuprite, Moffett Field, Jasper Ridge ve Pavia University hiperspektral görüntüleri üzerinde önerilen yöntem, ışıklılık dönüşümünün farklı versiyonları ile karşılaştırılmıştır. Karşılaştırma sinyal-gürültü oranı ve ortalama spektral açı uzaklığı gibi ölçütler kullanılarak yapılmıştır. Bunun yanında, sıkıştırılan verideki anomali ve hedef tespiti başarımları dakarşılaştırılmıştır. Önerilen yöntemin, 3D-DCT sıkıştırma performansını özellikle düşük bit oranlarında ortalama %40 oranına kadar arttırdığı gösterilmiştir.

Anahtar Kelimeler

Hiperspektral görüntüler, Sıkıştırma, Ayrık kosinüs dönüşümü, Işıklılık dönüşümü

Kaynakça

• [1]Öztürk Ş, Esin Y, Artan Y, Özdil Ö, Demirel B. “Importance of band selection for ethene and methanol gas detection in hyperspectral imagery”. 9thWorkshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), Amsterdam, Netherlands, 23-26 September 2018.
• [2]Xu Y, Wu Z, Wei Z, Dalla Mura M, Chanussot J, Bertozzi A. “Gasplume detection in hyperspectral video sequence using low rank representation”. IEEE2016International Conference on Image Processing (ICIP), Phoenix, USA, 25-28 September 2016.
• [3]Çeşmeci D, Karaca AC, Ertürk A, Güllü MK, Ertürk S. “Hyperspectral change detection by multi-band census transform”. IEEE2018Geoscience and Remote Sensing Symposium, Quebec City, Canada, 13-18 July 2018.
• [4]Kumar JP, Deshpande S, Inamdar A. “Detection of fertilizer quantity in soil using hyperspectral data”. 9thWorkshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), Amsterdam, Netherlands, 23-26 September 2018.
• [5]Zhao Y, Wang Y, Wei D, Mu H, Ning T. “Application of hyperspectral imaging in measurement real-time of seeds”. IEEE 2016International Conference on Smart Cloud, New York, NY, 18-20 November 2016.
• [6]Liang Y, Markopoulos PP, Saber ES. “Subpixel target detection in hyperspectral images with local matched filtering in SLIC superpixels”. 8thWorkshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), Los Angeles, USA, 21-24 August2016.
• [7]Ben Salem M, Ettabaa KS, Bouhlel MS. “Anomaly detection in hyperspectral images based spatial spectral classification”. 7thInternational Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT), Hammamet, Tunusia,18-26 December2016.
• [8]Xu H, Wang XJ. “Applications of multispectral hyperspectral ımaging technologies ın military”.Infrared And Laser Engineering, 36(1), 13-18, 2007.
• [9]Weijtmans PJC, Shan C, Tan T, Brouwer de Koning SG, Ruers TJM. “A duel stream network for tumordetection in hyperspectral ımages”. IEEE 16thInternational Symposium on Biomedical Imaging, Venice, Italy, 8-11 April2019.
• [10]Pike R, Lu G, Wang D, Chen ZG, Fei B. “A minimum spanning forest-based method for noninvasive cancer detection with hyperspectral imaging”. IEEE Transactions on Biomedical Engineering, 63(3), 653-663, 2016.
• [11]Christophe E, “Hyperspectral Data Compression Tradeoff, In: Prasad S, Bruce L, Chanussot J, Optical Remote Sensing”. Augmented Vision and Reality, 3(1), 9-29, 2011.
• [12]Pennebaker WB,Mitchell JL. JPEG: Still image data compression standard. 2nded. New York, USA, Springer Verlag,2006.
• [13]Schelkens, Peter, Athanassios Skodras, and Touradj Ebrahimi.The JPEG 2000 Suite.1sted. West Sussex, United Kingdom, John Wiley & Sons, 2009.
• [14]Abousleman GP, Marcellin MW, Hunt BR. “Compression of hyperspectral imagery using the 3-D DCT and hybrid DPCM/DCT”. IEEE Transactions onGeoscienceand Remote Sensing, 33(1), 26-34, 1995.
• [15]Thyagarajan K. S. Still Image Video Compression with MATLAB, 1sted.New Jersey, USA, John Wiley & Sons,2011.
• [16]Yıldız K, Buldu A. “Wavelet transform and principal component analysis in fabric defect detection and classification”. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 23(5), 622-627, 2016.
• [17]Penna B, Tillo T, Magli E, Olmo G. “Transform coding techniques for lossy hyperspectral data compression”. IEEE Transactions on Geoscience and Remote Sensing, 45(5), 1408-1421, 2007.
• [18]Mei S, Khan BM, Zhang Y,e Du Q. “Low-complexity hyperspectral image compression using foldedPCA and JPEG2000”. IEEE 2018 International Geoscience and Remote Sensing Symposium (IGARSS), Valencia, Spain, 22-27 July2018.
• [19]Tang X, Pearlman WA. Three-dimensional wavelet-basedcompression of hyperspectral images. Editors: Motta G, Rizzo F, Storer JA.Hyperspectral Data Compression, 273-308,Boston, USA, Springer US,2006.
• [20]Lim, S, Sohn K, Lee C. “Compression for hyperspectral ımages using three dimensional wavelet transform”. IEEE2001International Geoscience and Remote Sensing Symposium (IGARSS), Sydney, Australia, 9-13 July 2001.
• [21]Wang, Y, Rucker JT, Fowler JE. “Three-dimensional tarp coding for the compression of hyperspectral images”.IEEE Geoscience and Remote Sensing Letters, 1(2), 136-140, 2004.
• [22]Hassanzadeh S, Karami A. “Compression and noisereduction of hyperspectral images using non-negative tensor decomposition and compressed sensing”. European Journal of Remote Sensing, 49(1), 587-598, 2016.
• [23]Huber-Lerner M, Hadar O, Rotman SR, Huber-Shalem R. “Compression of hyperspectral images containing a subpixel target”. IEEEJournal Of Selected Topics in Applıed Earth Observatıons and Remote Sensıng, 7(6), 2246-2255, 2014.
• [24]Santos L, López S, Callico GM, Lopez JF, Sarmiento R. “Performance evaluation of the H. 264/AVC video coding standard for lossy hyperspectral image compression”. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2), 451-461, 2011.
• [25]Qiao T, Ren J, Sun M, Zheng J, Marshall S. “Effective compression of hyperspectral imagery using an improved 3D DCT approach for land-cover analysis in remote-sensing applications”. International Journal of Remote Sensing, 35(20), 7316-7337, 2014.
• [26]Karami A, Behesti S, Yazdi M. “Hyperspectral image compression using 3D discrete cosine transform and support vector machine learning”. 11thInternational Conference on Information Science, Signal Processing and their Applications (ISSPA), Canada, Montreal, 3-5 July2012.
• [27]Karami A, Yazdi M, Asli AZ. “Hyperspectral ımage compression based on tucker decomposition and discrete cosine transform”. 2nd International Conference on Image Processing Theory, Tools and Applications, Paris, France, 7-10 July 2010.
• [28]Haiyan T, Wenbang S, Bingzhe G, Fengjing Z. “Research on quantization and scanning order for 3-D DCT video coding”. International Conferenceon Computer Science and Electronics Engineering, Hangzhou, China, 23-25 March 2012.
• [29]Engin MA, Cavusoglu B. “New approach in image compression: 3D spiral JPEG”. IEEE Communications Letters, 15(11), 1234-1236, 2011.
• [30]Can E, Karaca AC, Danışman M, Urhan O, Güllü MK. “Compression of hyperspectral images using luminance transform and 3D-DCT”. IEEE2018 International Geoscience and Remote Sensing Symposium,Valencia, Spain, 22-27 July 2018.
• [31]Can E, Karaca AC, Danışman M, Urhan O, Güllü MK. “Compression of hyperspectral images using adaptive luminance transform”. 26th IEEE Signal Processing and Communications Applications Conference(SIU2018),İzmir, Turkey, 2-5 Mayıs 2018.
• [32]Du Q, Zhu W, Yang H, Fowler JE. “Segmented principal component analysis for parallel compression of hyperspectral imagery”. IEEE Geoscience and Remote Sensing Letters, 6(4), 713-717, 2009.
• [33]Zhou S, Xu Z, Liu F, “Method for determining the optimal number of clusters based on agglomerative hierarchical clustering”. IEEE Transactions on Neural Networks and Learning Systems,28(12), 3007-3017, 2017.
• [34]Murtagh F, Contreras P. “Algorithms for hierarchical clustering: an overview”. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2(1), 86-97, 2012.
• [35]Gerçek D, Çeşmeci D, Güllü MK, Ertürk A, Ertürk S, “Automated co-registeration of satellite images through luminance transform”. The Photogrammetric Record, 31(156), 407-427, 2016.
• [36]Kwon HJ, Lee SH, Lee GY, Sohng KL, “Luminance adaptation transform based on brightness functions for LDR image reproduction”. Digital Signal Processing,30(1), 74-85, 2014.
• [37]Skretting K. “MATLAB’da Huffman ve Aritmetik Kodlama”.http://www.ux.uis.no/~karlsk/proj99/index.html(01.07.2019).
• [38]Du Q, Ly N, Fowler JE. “An operational approach to PCA+JPEG2000 compression of hyperspectral imagery”.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6), 2237-2245, 2014.
• [39]Wang Z, Bovik A, Sheikh H, Simoncelli E. “Image quality assessment: from error visibility to structural similarity”. IEEE Transaction onImage Processing, 13(4),600-612, 2004.
• [40]Li W, Wu G, Du Q.“Transferred deep learning for anomaly detection in hyperspectral imagery”. IEEE Geoscienceand Remote Sensing Letters,14(5), 597-601, 2017.
• [41]Reed I, Yu X.“Adaptive multiple-band cfar detection of an optical pattern with unkown spectral distrubition”. IEEE Transactions on Acoustics, Speech, and Signal Processing,38(1), 1760-1770, 1990.