Hiperspektral görüntüler için değiştirilmiş SLIC tabanlı süperpiksel bölütleme

Year 2023, Volume: 38 Issue: 1, 399 - 408, 21.06.2022

İbrahim Onur Sığırcı , Gokhan Bılgın

https://doi.org/10.17341/gazimmfd.835846

Abstract

Basit doğrusal iteratif kümeleme (SLIC) süperpiksel algoritması, bölütleme için verimli ve hızlı bir algoritmadır. Bu algoritma doğası gereği üç bantlı renkli görüntüler için tasarlanmıştır. Uzaktan algılamada yeni bir teknoloji olan hiperspektral görüntüleme, zengin spektral ve uzamsal bilgi taşıyan yüzlerce bant içermektedir. Bu çalışmada, SLIC algoritması hiperspektral görüntülerin yapısına göre değiştirilmiştir. Buna ek olarak, benzer süperpikseller DBSCAN (gürültülü uygulamaların yoğunluk tabanlı uzamsal kümelenmesi) algoritması ile birleştirilmiştir. Esinlenen yeni bir yaklaşımla süperpikseller arasındaki spektral benzerlik indeksi, evrensel görüntü kalitesi indeksine göre hesaplanmıştır. Elde edilen bölütleme haritalarının sınıflandırma performansına katkısı karşılaştırılmalı olarak sunulmuştur.

Keywords

Süperpiksel bölütleme, hiperspektral sınıflandırma, , Hyper-SLIC, spektral-uzamsal, görüntü kalite indeksi

Supporting Institution

Yıldız Teknik Üniversitesi - Bilimsel Araştırma Projeleri Koordinatörlüğü

Project Number

2014-04-01-KAP01

Thanks

Bu çalışma Yıldız Teknik Üniversitesi Bilimsel Araştırma Projeleri Koordinatörlüğü Bölümü tarafından, 2014-04-01-KAP01 proje numarası ile desteklenmiştir.

A modified SLIC-based superpixel segmentation for hyperspectral images

Abstract

The SLIC (simple linear iterative clustering) superpixel algorithm is an efficient and fast algorithm for segmentation. The algorithm is inherently designed on three band color images. Hyperspectral imaging, which is a relatively new remote sensing technology, contains hundreds of bands which carry rich spectral and spatial information. In this study, the SLIC algorithm is modified according to the structure of hyperspectral images. In addition to that, the similar superpixels are merged with the DBSCAN (density-based spatial clustering of applications with noise) algorithm. As a novel inspired approach, the spectral similarity index between the superpixels are computed based on the universal image quality index. The contribution of the obtained segmentation maps to the classification performance is presented comparatively.

Keywords

Superpixel segmentation, , hiperspektral sınıflandırma, Hyper-SLIC, spectral-spatial, image quality index

Project Number

2014-04-01-KAP01

References

• 1. J. Ham, Y. Chen, M. M. Crawford, and J. Ghosh, Investigation of the random forest framework for classification of hyperspectral data, IEEE Transaction on Geoscience and Remote Sensing, 43 (3), 492–501, 2005.
• 2. E. Arzuaga-Cruz, L. O. Jimenez-Rodriguez, and M. Velez-Reyes, Unsupervised feature extraction and band subset selection techniques based on relative entropy criteria for hyperspectral data analysis, in Proceeding of SPIE, 5093, 462–473, 2003.
• 3. S. Kawaguchi and R. Nishii, Hyperspectral image classification by bootstrap adaboost with random decision stumps, IEEE Transaction on Geoscience and Remote Sensing, 45 (11), 3845–3851, 2007.
• 4. F. Melgani and L. Bruzzone, Classification of hyperspectral remote sensing images with support vector machines, IEEE Transaction on Geoscience and Remote Sensing, 42 (8), 1778–1790, 2004.
• 5. J. Li, J. M. Bioucas-Dias, and A. Plaza, Spectral–spatial classification of hyperspectral data using loopy belief propagation and active learning, IEEE Transaction on Geoscience and Remote Sensing, 51(2), 844–856, 2013.
• 6. G. Camps-Valls and L. Bruzzone, Kernel-based methods for hyperspectral image classification, IEEE Transaction on Geoscience and Remote Sensing, 43(6), 1351–1362, 2005.
• 7. K. Hanbay, Hyperspectral image classification using convolutional neural network and twodimensional complex Gabor transform. Journal of the Faculty of Engineering and Architecture of Gazi University. 35 (1), 443-456, 2019.
• 8. D. Hong, L. Gao, J. Yao, B. Zhang and A. Plaza, J. Chanussot, Graph convolutional networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 2020.
• 9. Y. Tarabalka, J. Chanussot, and J. A. Benediktsson, Classification based marker selection for watershed transform of hyperspectral images, in IEEE International on Geoscience and Remote Sensing Symposium, IGARSS’09, 3, III–105, 2009.
• 10. B. Fulkerson, A. Vedaldi, and S. Soatto, Class segmentation and object localization with superpixel neighborhoods, in IEEE 12th International Conference on Computer Vision (ICCV’09), 670–677, 2009.
• 11. K.-Y. Chang, T.-L. Liu, H.-T. Chen, and S.-H. Lai, Fusing generic objectness and visual saliency for salient object detection, in IEEE International Conference on Computer Vision (ICCV’11), 914–921, 2011.
• 12. S. Wang, H. Lu, F. Yang, and M.-H. Yang, Superpixel tracking, in IEEE International Conference on Computer Vision (ICCV), 1323–1330, 2011.
• 13. A. Karaca and M. Güllü, Detection of forest fire in Menderes district using a superpixel segmentation based search method. Journal of the Faculty of Engineering and Architecture of Gazi University, 34 (2), 1061-1076, 2019.
• 14. W. Huang, Y. Huang, H. Wang, Y. Liu and H. J. Shim, Local binary patterns and superpixel-based multiple kernels for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 4550-4563, 2020.
• 15. Y. Zhang, X. Jiang, X. Wang and Z. Cai, Spectral-spatial hyperspectral image classification with superpixel pattern and extreme learning machine. Remote Sensing, 11 (17), 1983, 2019.
• 16. L. Fang, S. Li, W. Duan, J. Ren, and J. A. Benediktsson, Classification of hyperspectral images by exploiting spectral–spatial information of superpixel via multiple kernels, IEEE Transaction on Geoscience and Remote Sensing, 53(12), 6663–6674, 2015.
• 17. R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, Slic superpixels compared to state-of-the-art superpixel methods, IEEE Transaction on Pattern Analysis and Machine Intelligence, 34, 2274–2282, 2012.
• 18. M. Ester, H.-P. Kriegel, J. Sander, X. Xu, et al., A density-based algorithm for discovering clusters in large spatial databases with noise., in KDD, 96, 226–231, 1996.
• 19. Z. Wang and A. C. Bovik, A universal image quality index, IEEE Signal Processing Letters, 9(3), 81–84, 2002.
• 20. J. Wang and C.-I. Chang, Independent component analysis-based dimensionality reduction with applications in hyperspectral image anal., IEEE Transaction on Geoscience and Remote Sensing, 44 (6), 1586–1600, 2006.
• 21. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, Scikit-learn: machine learning in Python, Journal of Machine Learning Research, 12, 2825–2830, 2011.
• 22. S. van der Walt, J. L. Schönberger, J. Nunez-Iglesias, F. Boulogne, J. D. Warner,N. Yager, E. Gouillart, T. Yu, and the scikit-image contributors, scikit-image:image processing in Python, PeerJ, 2 (e453), 2014.