KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Hyperspectral Image Classification via Joint Sparse representation of Multi-layer Superpixles

  • Sima, Haifeng (Department of Computer science and technology, Henan Polytechnic University) ;
  • Mi, Aizhong (Department of Computer science and technology, Henan Polytechnic University) ;
  • Han, Xue (Department of Computer science and technology, Henan Polytechnic University) ;
  • Du, Shouheng (Department of Computer science and technology, Henan Polytechnic University) ;
  • Wang, Zhiheng (Department of Computer science and technology, Henan Polytechnic University) ;
  • Wang, Jianfang (Department of Computer science and technology, Henan Polytechnic University)
  • Received : 2017.11.24
  • Accepted : 2018.03.20
  • Published : 2018.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a novel spectral-spatial joint sparse representation algorithm for hyperspectral image classification is proposed based on multi-layer superpixels in various scales. Superpixels of various scales can provide complete yet redundant correlated information of the class attribute for test pixels. Therefore, we design a joint sparse model for a test pixel by sampling similar pixels from its corresponding superpixels combinations. Firstly, multi-layer superpixels are extracted on the false color image of the HSI data by principal components analysis model. Secondly, a group of discriminative sampling pixels are exploited as reconstruction matrix of test pixel which can be jointly represented by the structured dictionary and recovered sparse coefficients. Thirdly, the orthogonal matching pursuit strategy is employed for estimating sparse vector for the test pixel. In each iteration, the approximation can be computed from the dictionary and corresponding sparse vector. Finally, the class label of test pixel can be directly determined with minimum reconstruction error between the reconstruction matrix and its approximation. The advantages of this algorithm lie in the development of complete neighborhood and homogeneous pixels to share a common sparsity pattern, and it is able to achieve more flexible joint sparse coding of spectral-spatial information. Experimental results on three real hyperspectral datasets show that the proposed joint sparse model can achieve better performance than a series of excellent sparse classification methods and superpixels-based classification methods.

Keywords

References

  1. Zhang, E.; Zhang, X.; Jiao, L.; Li, L.; Hou, B. "Spectral-spatial hyperspectral image ensemble classification via joint sparse representation," Pattern Recognition, vol. 59, pp. 42-54, 2016. https://doi.org/10.1016/j.patcog.2016.01.033
  2. Bruzzone, L.; Chi, M.; and Marconcini, M. "A novel transductive SVM for semisupervised classification of remote-sensing images," IEEE Trans. Geosci. Remote Sens., vol. 44, pp. 3363-3373, 2006. https://doi.org/10.1109/TGRS.2006.877950
  3. Zhong, Y.; Lin, Y.; and Zhang, L. "A support vector conditional random classifier with a Mahalanobis distance boundary constraint for high spatial resolution remotes sensing imagery," IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 7, pp.1314-1333, 2014.
  4. Hao S, Wang W, Yan Y, et al. "Class-wise dictionary learning for hyperspectral image classification," Neurocomputing, vol. 220, pp. 121-129, 2017. https://doi.org/10.1016/j.neucom.2016.05.101
  5. Krishnapuram, B.; Carin, L.; Figueiredo,M.; and Hartemink, A. "Sparse multinomial logistic regression: Fast algorithms and generalization bounds," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 27, pp. 957-968, 2005. https://doi.org/10.1109/TPAMI.2005.127
  6. Li,J.; Bioucas-Dias, J. M.; and Plaza, A. "Semi-supervised hyperspectral image classification using soft sparse multinomial logistic regression," IEEE Geosci. Remote Sens. Lett., vol. 10, pp. 318- 322, 2013. https://doi.org/10.1109/LGRS.2012.2205216
  7. Du B.; Zhang L.; Chen T.; Wu, K. "A discriminative manifold learning based dimension reduction method for hyperspectral classification," International J Fuzzy Syst., vol. 14, pp.272-277, 2012.
  8. Li, W.; Prasad, S.; Fowler, J.E.; Bruce, L.M. "Locality-Preserving Dimensionality Reduction and Classification for Hyperspectral Image Analysis," IEEE Transactions on Geoscience & Remote Sensing, vol. 50, pp.1185-1198, 2012. https://doi.org/10.1109/TGRS.2011.2165957
  9. Chen, Y.N.; Hsieh, C.T.; Wen, M. G.; Han, C.C.; Fan, K.C. "A Dimension Reduction Framework for HSI Classification Using Fuzzy and Kernel NFLE Transformation," Remote Sensing, vol. 7, pp. 14292-14326, 2015. https://doi.org/10.3390/rs71114292
  10. Song, X.F.; Jiao, L.C.; Yang, S.Y.; Zhang, X. R.; Shang, F.H. "Sparse coding and classifier ensemble based multi-instance learning for image categorization," Signal Process. vol. 93, pp.1-11, 2013. https://doi.org/10.1016/j.sigpro.2012.07.029
  11. Ham,J.; Chen; Y.C.; Crawford, M.M.; Ghosh, J. "Investigation of the random forest framework for classification of hyperspectral data," IEEE Trans. Geosci. Remote Sens. vol. 43, pp. 492-501, 2005. https://doi.org/10.1109/TGRS.2004.842481
  12. Wright, J., Yang, A.Y.; Ganesh, A.; Sastry, S.; and Ma, Y. "Robust face recognition via sparse representation," IEEE Trans. Pattern Anal. Mach.Intell, vol. 31, pp.210-227, 2009. https://doi.org/10.1109/TPAMI.2008.79
  13. Mairal,J.; Elad, M.; Sapiro, G. "Sparse representation for color image restoration," IEEE Trans. Image Process. vol. 17, pp. 53-69, 2008. https://doi.org/10.1109/TIP.2007.911828
  14. Nasrabadi, N. M. "Hyperspectral Target Detection : An Overview of Current and Future Challenges," IEEE Signal Process. Mag., vol. 31, pp. 34-44, 2013 .
  15. Moayedi, F.; Azimifar, Z.; Boostani, R. "Structured sparse representation for human action recognition," Neuro computing, vol. 161, pp. 38-46, 2015.
  16. Ma, W.K.;Bioucas-Dias, J.M.; Chan,T.H.; Gillis, N.; Gader, P.; Plaza,A.J.; Ambikapathi, A.; Chi, C.Y. "A signal processing perspective on hyperspectral unmixing," IEEE Signal Process. Mag. vol. 31, pp. 67-81, 2014. https://doi.org/10.1109/MSP.2013.2279731
  17. Chen, Y.; Nasrabadi, N.M.; Tran, T. D. "Hyperspectral image classification using dictionary-based sparse representation," IEEE Geosci. Remote Sens. vol. 49, pp.3973-3985, 2011. https://doi.org/10.1109/TGRS.2011.2129595
  18. Chen,Y.; Nasrabadi,N. M.; Tran T. D. "Hyperspectral image classification via kernel sparse representation," IEEE Geosci. Remote Sens," vol. 51, pp. 217-231, 2013. https://doi.org/10.1109/TGRS.2012.2201730
  19. Zhang, H.Y.; Li, J.Y.; Huang, Y.C.; Zhang, L.P. "A nonlocal weighted joint sparse representation classification method for hyper-spectral imagery," IEEE J. Sel. Topics Appl. Earth Observat. Remote Sens. vol. 7, pp.2056-2065, 2014. https://doi.org/10.1109/JSTARS.2013.2264720
  20. Peng J, Du Q. Robust Joint Sparse Representation Based on Maximum Correntropy Criterion for Hyperspectral Image Classification. IEEE Transactions on Geoscience & Remote Sensing, PP(99):1-13, 2017.
  21. Fang, L.Y.; Li, S.T.; Kang, X.D.; Benediktsson, J.A. "Spectral-spatial hyperspectral image classification via multiscale adaptive sparse representation," IEEE Trans. Geosci. Remote Sens. vol.52, pp.7738-7749, 2014. https://doi.org/10.1109/TGRS.2014.2318058
  22. Fang, L.Y.; Li, S.; Duan, W.; Ren, J. "Classification of Hyperspectral Images by Exploiting Spectral Spatial Information of Superpixel via Multiple Kernels," IEEE Trans. Geosci. Remote Sens. 2015, vol. 53, pp.6663-6674. https://doi.org/10.1109/TGRS.2015.2445767
  23. Fang L.Y., Li S.; Kang X.; Benediktsson, J.A. "Spectral-Spatial Classification of Hyperspectral Images With a Superpixel-Based Discriminative Sparse Model," IEEE Trans. Geosci. Remote Sens. vol. 53, pp.4186-4201, 2015. https://doi.org/10.1109/TGRS.2015.2392755
  24. Peng, J.; Luo, T. "Sparse matrix transform-based linear discriminant analysis for hyperspectral image classification," Signal, Image and Video Processing, vol.10, pp.1-8, 2016. https://doi.org/10.1007/s11760-014-0693-9
  25. Zhai, Y.; Zhang, L.; Wang N.; Guo, Y. "A Modified Locality-Preserving Projection Approach for Hyperspectral Image Classification," IEEE Trans. Geosci. Remote Sens. Lett., vol. 13, pp. 1-5, 2016. https://doi.org/10.1109/LGRS.2015.2509518
  26. Li X, Liu K, Dong Y. "Superpixel-Based Foreground Extraction with Fast Adaptive Trimaps," IEEE Transactions on Cybernetics, PP(99):1-11, 2017.
  27. Sima H, Guo P. "Texture superpixels merging by color-texture histograms for color image segmentation," Ksii Transactions on Internet & Information Systems, 8(7):2400-2419, 2014. https://doi.org/10.3837/tiis.2014.07.011
  28. Dong Y, Tao D, Li X, et al. "Texture Classification and Retrieval Using Shearlets and Linear Regression," IEEE Transactions on Cybernetics, 45(3):358-369, 2015. https://doi.org/10.1109/TCYB.2014.2326059
  29. Li X, Kang L, Dong Y, et al. Patch Alignment Manifold Matting. "IEEE Trans Neural Netw Learn Syst, " PP(99):1-13, 2017.
  30. Huang, H.; Yang, M. "Dimensionality Reduction of Hyperspectral Images With Sparse Discriminant Embedding," IEEE Trans. Geosci. Remote Sens., vol. 53, pp. 5160-5169, 2015. https://doi.org/10.1109/TGRS.2015.2418203
  31. Felzenszwalb, P.F.; Huttenlocher, D. P. "Efficient Graph-Based Image Segmentation. Internation al Journal of Computer Vision," Int. J. comput. vis., vol. 59, pp. 167-181, 2004.
  32. Comaniciu,D.; Meer, P. "Mean shift: a robust approach toward feature space analysis," IEEE Trans. Pattern Anal. Mach.Intell., vol.24, pp. 603-619, 2002. https://doi.org/10.1109/34.1000236
  33. Achanta, R.; Shaji,A.; Smith, K.; Lucchi, A.; Fua, P.; SuSstru, S. "SLIC superpixels compared to state-of-the-art superpixel methods," IEEE Trans. Pattern Anal. Mach.Intell. vol. 34, pp. 2274-2282, 2012. https://doi.org/10.1109/TPAMI.2012.120
  34. Yuan, X.T.; Liu, X.; Yan, S. "Visual classification with multitask joint sparse representation". IEEE Transaction on Image Process, vol. 21, pp. 4349-4360, 2015.
  35. Duarte,M. F.; Sarvotham ,S.; Baron, D.; Wakin, M.B. "Distributed Compressed Sensing of Jointly Sparse Signals," in Proc. of Proceedings of the IEEE Conference of the Thirty-Ninth Asilomar Conference On signals, Systems and Computers, pp. 1537-1541, 2005.
  36. Hu, Z.P.; Bai, F.; Zhao; S.H.; Wang, M.; Sun, Z. "Extended common molecular and discriminative atom dictionary based sparse representation for face recognition," J of Vis. Commun. Image R., vol. 40, pp.42-50, 2016. https://doi.org/10.1016/j.jvcir.2016.05.019
  37. Richards J .A., Jia X. P., Richards J A. "In Remote sensing digital image analysis: an introduction," Remote sensing digital image analysis, vol. 40, pp.47-54. 2016.
  38. Tropp, J.; Gilbert, A. "Signal recovery from random measurements via orthogonal matching pursuit," IEEE Trans. Inf. Theory, vol. 53, pp. 4655-4666, 2007. https://doi.org/10.1109/TIT.2007.909108
  39. Chang S F, Wu X M, Li Z. "Segmentation using superpixels: A bipartite graph partitioning approach," in Proc. of Proceedings of the IEEE Conference of the Computer Vision and Pattern Recognition, June, pp. 789-796, 2012.
  40. Smith L. I. "A Tutorial on Principal Components Analysis," Information Fusion, vol. 51, 52, 2002.
  41. Töksoz, M.A.; Ilkay Ulusoy. "Hyperspectral Image Classification via Basic Thresholding Classifier," IEEE Trans. on Geosci. Remote Sens., vol.54, pp. 4039-4051, 2016. https://doi.org/10.1109/TGRS.2016.2535458
  42. Tropp J A. "Algorithms for simultaneous sparse approximation: part II: Convex relaxation[M]," Elsevier North-Holland, Inc. 2006.