LiDAR-Tabanlı toplam değişinti kısıtlı negatif-olmayan tensör faktörizasyonu ile hiperspektral karışım giderimi

Abstract

Spektral karışım giderimi hiperspektral görüntülemenin temel araştırma alanlarından birisidir. Son yıllarda Negatif-olmayan Tensör Faktörizasyonuna dayalı yaklaşımlar, bilgi kaybına uğratmadığı ve hiperspektral görüntüleri daha iyi temsil edebildiği için uzaktan algılamada büyük bir önem kazanmıştır. Toplam Değişinti yaklaşımı ise, parçalı pürüzsüzlüğü sağlarken kenar bilgisini de korumaktadır. Öte yandan, kızılötesi algılayıcısı gözlemlenen sahne hakkında yükseklik bilgisini veren Dijital Yüzey Modeli verisini sağlamaktadır. Bu çalışmada, LiDAR Dijital Yüzey Modeli bilgisiyle Toplam Değişinti kısıtı birleştirilerek hiperspektral görüntülerin uzamsal çözünürlüğünü artırmak için tensör faktörizasyonuna dayalı karışım giderimi gerçekleştirilmiştir. Deneysel çalışmalar simülasyon ve gerçek veri setleri üzerinde denenmiş ve uzamsal çözünürlüğü artırılmış hiperspektral görüntüler elde edilmiştir. Elde edilen sonuçlar, literatürdeki en yakın çalışma olan Toplam Değişinti kısıtlı Negatifolmayan Matris-Vektör Tensor Faktörüzasyonu yöntemi ile karşılaştırılmış ve önerilen yöntemin daha iyi performans sergilediği gözlemlenmiştir.

Keywords

• Hiperspektral görüntü
• Kızılötesi
• Veri kaynaştırma
• Spektral karışım giderimi
• Toplam değişinti

Hyperspectral unmixing with LiDAR-Based total variation regularized non-negative tensor factorization

Abstract

Spectral unmixing is one of the main research areas of hyperspectral image analysis. In recent years, Non-Negative Tensor Factorization based approaches have gained great importance in remote sensing as they do not lose information and can better represent hyperspectral images. The Total Variation approach preserves the edge information while providing piece-wise smoothness. On the other hand, the Light Detection and Ranging sensor provides Digital Surface Model information that gives height information about the observed scene. In this study, hyperspectral unmixing based on tensor factorization is performed to increase the spatial resolution of hyperspectral images by combining LiDAR Digital Surface Model information with Total Variation constrained. Experimental studies are carried out on simulation and real data sets and high spatial resolution hyperspectral images is obtained. The obtained results is compared with the state of the art Total Variation constrained Matrix-Vector Non-Negative Tensor Factorization approach and it is observed that the proposed method obtain better performance.

Keywords

• Hyperspectral image
• Light detection and ranging
• Data fusion
• Spectral unmixing
• Total variation

References

1. [1] Nasrabadi NM. “Hyperspectral target detection: An overview of current and future challenges”. IEEE Signal Processing Magazine, 31(1), 34-44, 2014.
2. [2] Camps-Valls G, Tuia D, Bruzzone L, Benediktsson JA. “Advances in hyperspectral image classification: Earth monitoring with statistical learning methods”. IEEE Signal Processing Magazine, 31(1), 45-54, 2014.
3. [3] Bioucas-Dias JM, Plaza A, Dobigeon N, Parente M, Du Q, Gader P, Chanussot J. “Hyperspectral unmixing overview: Geometrical, statistical, and sparse regression-based approaches”. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2), 354-379, 2012.
4. [4] Keshava N, Mustard JF. “Spectral unmixing”. IEEE Signal Processing Magazine, 19(1), 44-57, 2002.
5. [5] Lee D, Seung H. “Learning the parts of objects by nonnegative matrix actorization”. Nature, 401, 788-791, 1999.
6. [6] Lee D, Seung H. “Algorithms for non-negative matrix factorization”. Advances in Neural Information Processing Systems, 13, 556-562, 2001.
7. [7] Pauca VP, Piper J, Plemmons RJ. “Nonnegative matrix factorization for spectral data analysis”. Linear Algebra and its Applications, 416, 29-47, 2006.
8. [8] Iordache MD, Bioucas-Dias JM, Plaza A. “Total variation spatial regularization for sparse hyperspectral unmixing”. IEEE Transactions on Geoscience and Remote Sensing, 50(11), 4484-4502, 2012.

9. [9] Cichocki A, Mandic DP, Phan AH, Caiafa CF, Zhou G, Zhao Q, Lathauwer LD. “Tensor decompositions for signal processing applications: From two-way to multiway component analysis”. IEEE Signal Processing Magazine, 32(2), 145-163, 2015.
10. [10] Kolda TG, Bader BW. “Tensor decompositions and applications”. Society for industrial and applied mathematics, 51(3), 455-500, 2009.
11. [11] Yokota T, Zhao Q, Cichocki A. “Smooth PARAFAC decomposition for tensor completion”. IEEE Transactions on Signal Processing, 64(20), 5423-5436, 2016.
12. [12] Hu W, Tao D, Zhang W, Xie Y, Yang Y. “The twist tensor nuclear norm for video completion”. IEEE Transactions on Neural Networks and Learning Systems, 28(12), 2961-2973, 2017.
13. [13] Narita A, Hayashi K, Tomioka R, Kashima H. “Tensor factorization using auxiliary information". Data Mining and Knowledge Discovery, 25(2), 298-324, 2012.
14. [14] Qian Y, Xiong F, Zeng S, Zhou J, Tang YY. “Matrix vector nonnegative tensor factorization for blind unmixing of hyperspectral imagery”. IEEE Transactions on Geoscience and Remote Sensing, 55(3), 1776-1792, 2017.
15. [15] Kahraman S, Bacher R. "A comprehensive review of hyperspectral data fusion with LiDAR and SAR data". Annual Reviews in Control, 51(2), 236 -253, 2021.
16. [16] Jung J, Pasolli E, Prasad S, Tilton JC, Crawford MM. “A framework for land cover classification using discrete return LiDAR data: Adopting pseudo-waveform and hierarchical segmentation”. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(2), 491-502, 2014.
17. [17] Luo R, Liao W, Zhang H, Zhang L, Scheunders P, Pi Y, Philips W. “Fusion of hyperspectral and LiDAR data for classification of cloud-shadow mixed remote sensed scene”. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(8), 3768-3781, 2017.
18. [18] Uezato T, Fauvel M, Dobigeon N. “Hyperspectral image unmixing with LiDAR data-aided spatial regularization”. IEEE Transactions on Geoscience and Remote Sensing, 56(7), 4098-4108, 2018.
19. [19] Yüksel SE, Boyacı M. “LiDAR sensörünün hiperspektral verilerden gölgelik alan çıkarımı başarımına etkisi”. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 24(2), 198-204, 2018.
20. [20] Xue Z, Yang S, Zhang H, Du P. “Coupled higher-order tensor factorization for hyperspectral and LiDAR data fusion and classification”. Remote Sensing, 11(17), 1-27, 2019.
21. [21] Li N, Pfeifer N, Liu C. “Airborne LiDAR points classification based on tensor sparse representation”. Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 4, 107-114, 2017.
22. [22] Li N, Liu C, Pfeifer N, Yin JF, Liao ZY, Zhou Y. “Tensor modelling based for airborne LiDAR data classification”. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 41, 283-287, 2016.
23. [23] Xiong F, Qian Y, Zhou J, Tang YY. “Hyperspectral unmixing via total variation regularized nonnegative tensor factorization”. IEEE Transactions on Geoscience and Remote Sensing, 57(4), 1-17, 2018.
24. [24] He S, Zhou H, Wang Y, Cao W, Han Z. “Super-resolution reconstruction of hyperspectral images via low rank tensor modeling and total variation regularization”. IEEE International Geoscience and Remote Sensing Symposium, Beijıng, China, 10-15 July 2016.
25. [25] Rasti B, Ghamisi P, Gloaguen R. “Hyperspectral and LiDAR fusion using extinction profiles and total variation component analysis”. IEEE Transactions on Geoscience and Remote Sensing, 55(7), 3997-4007, 2017.
26. [26] Hazan T, Polak S, Shashua A. “Sparse image coding using a 3D non-negative tensor factorization”. Tenth IEEE International Conference on Computer Vision, Beijing, China, 17-21 October 2005.
27. [27] Khan SA, Kaski S. “Bayesian multi-view tensor factorization”. Machine Learning and Knowledge Discovery in Databases, Nancy, France, 15-19 September 2014.
28. [28] Schaechtle U, Stathis K, Bromuri S. “Multi-dimensional causal discovery”. Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, Beijing, China, 3-9 August 2013.
29. [29] Imbiriba T, Borsoi RA, Bermudez JCM. “Low-rank tensor modeling for hyperspectral unmixing accounting for spectral variability”. IEEE Transactions on Geoscience and Remote Sensing, 58(3), 1833-1842, 2020.
30. [30] Ng MK-P, Yuan Q, Yan L, Sun J. “An adaptive weighted tensor completion method for the recovery of remote sensing images with missing data”. IEEE Transactions on Geoscience and Remote Sensing, 55(6), 3367-3381, 2017.
31. [31] He Z, Li J, Liu L. “Tensor block-sparsity based representation for spectral-spatial hyperspectral image classification”. Remote Sensing, 8(8), 1-21, 2016.
32. [32] Fan H, Chen Y, Guo Y, Zhang H, Kuang G. “Hyperspectral image restoration using low-rank tensor recovery”. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(10), 4589-4604, 2017.
33. [33] Lathauwer LD, Nion D. “Decompositions of a higher-order tensor in block terms-Part III: Alternating least squares algorithms”. Journal on Matrix Analysis and Applications, 30(3), 1067-1083, 2008.
34. [34] Cichocki A, Zdunek R, Phan AH, Amari S. Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation. Singapore,John Wiley & Sons, 2009.