Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Convolutional neural network in network (CNNiN): hyperspectral image classification and dimensionality reduction

© The Institution of Engineering and Technology
Received 23/12/2017, Accepted 31/03/2018, Revised 18/03/2018, Published 10/04/2018

Classification is a principle technique in hyperspectral images (HSIs), where a label is assigned to each pixel based on its characteristics. However, due to lack of labelled training instances in HSIs and also its ultra-high dimensionality, deep learning approaches need a special consideration for HSI classification. As one of the first works in the HSI classification, this study proposes a novel network pipeline called convolutional neural network in network (which is deeper than the existing approaches) by jointly utilising the spatial and spectral information and produces high-level features from the original HSI. This can occur by using spatial–spectral relationships of individual pixel vector at the initial component of the proposed pipeline; the extracted features are then combined to form a joint spatial–spectral feature map. Finally, a recurrent neural network is trained on the extracted features which contain wealthy spectral and spatial properties of the HSI to predict the corresponding label of each vector. The model has been tested on two large scale hyperspectral datasets in terms of classification accuracy, training error, and computational time.

Inspec keywords: hyperspectral imaging; learning (artificial intelligence); feature extraction; image classification; geophysical image processing; recurrent neural nets

Other keywords: HSI classification; dimensionality reduction; feature extraction; convolutional neural network in network; network pipeline; hyperspectral image classification; recurrent neural network; deep learning approach; CNNiN; spatial-spectral relationship

Subjects: Computer vision and image processing techniques; Knowledge engineering techniques; Geophysics computing; Image recognition; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Geophysical techniques and equipment; Neural computing techniques

References

    1. 1)
      • 29. Fukushima, K.: ‘Neocognitron: a hierarchical neural network capable of visual pattern recognition’, Neural Netw., 1988, 1, (2), pp. 119–130.
    2. 2)
      • 33. Makantasis, K., Karantzalos, K., Doulamis, A.D., et al: ‘Deep supervised learning for hyperspectral data classification through convolutional neural networks’. Proc. IEEE Int. Geoscience and Remote Sensing Symp., Milan, Italy, July 2015, pp. 4959–4962.
    3. 3)
      • 44. Hao, W., Saurabh, P.: ‘Convolutional recurrent neural networks for hyperspectral data classification’, Remote Sens., 2017, 9, 298, pp. 1–20.
    4. 4)
      • 15. Zhao, W., Du, S.: ‘Spectral–spatial feature extraction for hyperspectral image classification: A dimension reduction and deep learning approach’, IEEE Trans. Geosci. Remote Sens., 2016, 54, pp. 4544–4554.
    5. 5)
      • 35. Li, J., Marpu, P.R., Plaza, A., et al: ‘Generalized composite kernel framework for hyperspectral image classification’. IEEE Trans. Geosci. Remote Sens., 2013, 51, (9), pp. 4816–4829.
    6. 6)
      • 46. Jia, Y., Shelhamer, E., Donahue, J., et al: ‘Caffe: convolutional architecture for fast feature embedding’. Proc. ACM Int. Conf., New York, USA, 2014, pp. 675–678.
    7. 7)
      • 12. Chen, Y., Lin, Z., Zhao, X., et al: ‘Deep learning-based classification of hyperspectral data’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2014, 7, (6), pp. 2094–2107.
    8. 8)
      • 45. Krizhevsky, A., Sutskever, I., Hinton, G.: ‘ImageNet classification with deep convolutional neural networks’. Conf. on Neural Information Processing Systems (NIPS), New York, USA, 2012.
    9. 9)
      • 22. de Morsier, F., Borgeaud, M., Gass, V., et al: ‘Kernel low-rank and sparse graph for unsupervised and semi-supervised classification of hyperspectral images’, IEEE Trans. Geosci. Remote Sens., 2016, 54, pp. 3410–3420.
    10. 10)
      • 42. Sergey, I., Christian, S.: ‘Batch normalization: accelerating deep network training by reducing internal covariate shift’. Conf. on Machine Learning, JMLR Workshop & Conf. Proc., Lille, France, 2015, pp. 448–456.
    11. 11)
      • 27. Yuan, Y., Zheng, X., Lu, X.: ‘Spectral–spatial kernel regularized for hyperspectral image denoising’, IEEE Trans. Geosci. Remote Sens., 2015, 53, (7), pp. 3815–3832.
    12. 12)
      • 37. Zhao, W., Du, S.: ‘Spectral-spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (8), pp. 4544–4554.
    13. 13)
      • 40. Hyungtae, L., Heesung, K.: ‘Going deeper with contextual CNN for hyperspectral image classification’. arXiv:1604.03519v3 [cs.CV], 2017.
    14. 14)
      • 24. Yang, L., Wang, M., Yang, S., et al: ‘Sparse spatiospectral lapSVM with semisupervised kernel propagation for hyperspectral image classification’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2017, (99), pp. 1–9.
    15. 15)
      • 32. Dong, X., Shen, J., Shao, L., et al: ‘Sub-Markov random walk for image segmentation’, IEEE Trans. Image Process., 2016, 25, (2), pp. 516–527.
    16. 16)
      • 16. Yue, J., Zhao, W., Mao, S., et al: ‘Spectral-spatial classification of hyperspectral images using deep convolutional neural networks’, Remote Sens. Lett., 2015, 6, pp. 468–477.
    17. 17)
      • 47. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’. ICLR, arXiv:1409.1556 [cs.CV], 2015, pp. 1–14.
    18. 18)
      • 8. Ertürk, A., Iordache, M.-D., Plaza, A.: ‘Sparse unmixing-based change detection for multitemporal hyperspectral images’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2015, 9, (2), pp. 708–719.
    19. 19)
      • 25. Roscher, R., Waske, B.: ‘Shapelet-based sparse representation for landcover classification of hyperspectral images’, IEEE Trans. Geosci. Remote Sens., 2016, 54, pp. 1623–1634.
    20. 20)
      • 2. Zhu, Q., Zhong, Y., Zhao, B., et al: ‘Bag-of-visual words scene classifier with local and global features for high spatial resolution remote sensing imagery’, IEEE Geosci. Remote Sens. Lett., 2016, 13, (6), pp. 747–751.
    21. 21)
      • 1. Ghamisi, P., Mura, M.D., Benediktsson, J.A.: ‘A survey on spectral–spatial classification techniques based on attribute profiles’, IEEE Trans. Geosci. Remote Sens., 2015, 53, (5), pp. 2335–2353.
    22. 22)
      • 26. Tuia, D., Camps-Valls, G., Matasci, G., et al: ‘Learning relevant image features with multiple-kernel classification’, IEEE Trans. Geosci. Remote Sens., 2010, 48, (10), pp. 3780–3791.
    23. 23)
      • 7. Chen, Y., Zhao, X., Jia, X.: ‘Spectral–spatial classification of hyperspectral data based on deep belief network’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2015, 8, (6), pp. 2381–2392.
    24. 24)
      • 14. Deng, J., Dong, W., Socher, L.J.J.R., et al: ‘ImageNet: A large-scale hierarchical image database’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Miami, USA, 2009.
    25. 25)
      • 10. Mou, L., Ghamisi, P., Zhu, X.X.: ‘Deep recurrent neural networks for hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2017, 55, (7), pp. 3639–3655.
    26. 26)
      • 41. Clevert, D.A., Unterthiner, T., Hochreiter, S.: ‘fast and accurate deep network learning by exponential linear units (ELUs)’, ICLR 2016, arXiv:1511.07289.
    27. 27)
      • 19. Wang, Q., Gu, Y., Tuia, D.: ‘Discriminative multiple kernel learning for hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2016, 54, pp. 3912–3927.
    28. 28)
      • 43. Tim, C., Nicolas, B., César, L., et al: ‘Recurrent batch normalization’. Conf. at ICLR, Toulon, France, 2017.
    29. 29)
      • 4. Delalieux, S., Somers, B., Haest, B., et al: ‘Heathland conservation status mapping through integration of hyperspectral mixture analysis and decision tree classifiers’, Remote Sens. Environ., 2012, 126, pp. 222–231.
    30. 30)
      • 28. Zareapoor, M., Shamsolmoali, P., Jain, D.K., et al: ‘Kernelized support vector machine with deep learning: An efficient approach for extreme multiclass dataset’, Pattern Recognit. Lett., 2017, pp. 1–10.
    31. 31)
      • 3. Li, J., Khodadadzadeh, M., Plaza, A., et al: ‘A discontinuity preserving relaxation scheme for spectral–spatial hyperspectral image classification’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2016, 9, (2), pp. 625–639.
    32. 32)
      • 11. Li, T., Zhang, J., Zhang, Y.: ‘Classification of hyperspectral image based on deep belief networks’. IEEE Conf. on Image Processing (ICIP), Paris, France, 2014.
    33. 33)
      • 30. Cireşan, D.C., Meier, U., Masci, J., et al: ‘Flexible, high performance convolutional neural networks for image classification’. Proc. 22nd Int. Joint Conf. on Artificial Intelligence (IJCAI'11), San Francisco, USA, 2011, 22, pp. 1237–1242.
    34. 34)
      • 34. Wu, R., Yang, S., Leng, D., et al: ‘Random projected convolutional feature for scene text recognition’. IEEE 2016 15th Int. Conf. on Frontiers in Handwriting Recognition (ICFHR), Shenzhen, China, 2016, pp. 132–137.
    35. 35)
      • 9. Zhong, P., Gong, Z., Li, S., et al: ‘Learning to diversify deep belief networks for hyperspectral image classification’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2017, (99), pp. 1–15.
    36. 36)
      • 5. Ham, J., Chen, Y., Crawford, M.M., et al: ‘Investigation of the random forest framework for classification of hyperspectral data’, IEEE Trans. Geosci. Remote Sens., 2005, 43, (3), pp. 492–501.
    37. 37)
      • 21. Gu, Y., Liu, T., Jia, X., et al: ‘Nonlinear multiple kernel learning with multiple-structure-element extended morphological profiles for hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2016, 54, pp. 3235–3247.
    38. 38)
      • 18. Chen, Y., Nasrabadi, N.M., Tran, T.D.: ‘Hyperspectral image classification using dictionary-based sparse representation’, IEEE Trans. Geosci. Remote Sens., 2011, 49, (10), pp. 3973–3985.
    39. 39)
      • 36. Wang, X., Kong, Y., Gao, Y., et al: ‘Dimensionality reduction for hyperspectral data based on pairwise constraint discriminative analysis and nonnegative sparse divergence’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2017, 10, pp. 1552–1562.
    40. 40)
      • 31. Yuan, Y., Xiangtao, Z., Xiaoqiang, L.: ‘Hyperspectral image superresolution by transfer learning’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2017, 10, (5), pp. 1963–1974.
    41. 41)
      • 23. Liu, J., Wu, Z., Li, J., et al: ‘Probabilistic-kernel collaborative representation for spatial-spectral hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2016, 54, pp. 2371–2384.
    42. 42)
      • 13. Chen, Y., Jiang, H., Li, C., et al: ‘Deep feature extraction and classification of hyperspectral images based on convolutional neural networks’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (10), pp. 6232–6251.
    43. 43)
      • 17. Hu, W., Huang, Y., Wei, L., et al: ‘Deep convolutional neural networks for hyperspectral image classification’, J. Sens., 2015, 2015, pp. 1–12.
    44. 44)
      • 38. Zhang, H., Li, J., Huang, Y., et al: ‘A nonlocal weighted joint sparse representation classification method for hyperspectral imagery’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2014, 7, (6), pp. 2056–2065.
    45. 45)
      • 20. Gurram, P., Kwon, H.: ‘Sparse kernel-based ensemble learning with fully optimized kernel parameters for hyperspectral classification problems’, IEEE Trans. Geosci. Remote Sens., 2013, 51, pp. 787–802.
    46. 46)
      • 6. Melgani, F., Bruzzone, L.: ‘Classification of hyperspectral remote sensing images with support vector machines’, IEEE Trans. Geosci. Remote Sens., 2004, 42, (8), pp. 1778–1790.
    47. 47)
      • 39. Bengio, Y., Courville, A., Vincent, P.: ‘Representation learning: A review and new perspectives’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (8), pp. 1798–1828.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2017.1375
Loading

Related content

content/journals/10.1049/iet-ipr.2017.1375
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address