Unsupervised deep feature extraction for remote sensing image classification

IEEE Transactions on Geoscience and Remote Sensing

Volumn 54, Issue 3, 2016, Pages 1349-1362

  Romero, Adriana ^a   Gatta, Carlo ^b   Camps Valls, Gustau ^c  

^a UNIVERSITY OF BARCELONA   (Spain)

^b UNIVERSITAT AUTÒNOMA DE BARCELONA   (Spain)

^c UNIVERSITY OF VALENCIA   (Spain)

Author keywords

Aerial image classification; Classification; Deep convolutional networks; Deep learning; Feature extraction; Hyperspectral (HS) image; Multispectral (MS) images; Segmentation; Sparse features learning; Very high resolution (VHR)

Indexed keywords

ALGORITHMS; COMPLEX NETWORKS; CONVOLUTION; FEATURE EXTRACTION; IMAGE PROCESSING; IMAGE RECONSTRUCTION; LAND USE; LEARNING ALGORITHMS; NETWORK LAYERS; PRINCIPAL COMPONENT ANALYSIS; REMOTE SENSING; SPECTROSCOPY;

COMPUTATIONALLY EFFICIENT; CONVOLUTIONAL NETWORKS; DISCRIMINATIVE FEATURES; HYPER-SPECTRAL IMAGERIES; LAND COVER CLASSIFICATION; LANDUSE CLASSIFICATIONS; REMOTE SENSING IMAGE CLASSIFICATION; STATE-OF-THE-ART ALGORITHMS;

IMAGE CLASSIFICATION;

ARTIFICIAL NEURAL NETWORK; COMPLEXITY; IMAGE CLASSIFICATION; MULTISPECTRAL IMAGE; PRINCIPAL COMPONENT ANALYSIS; REMOTE SENSING; SEGMENTATION;

EID: 84940417789     PISSN: 01962892     EISSN: None     Source Type: Journal    
DOI: 10.1109/TGRS.2015.2478379     Document Type: Article

References (67)

1. S. Liang, Quantitative Remote Sensing of Land Surfaces. New York, NY, USA: Wiley, 2004.
2. T. M. Lillesand, R. W. Kiefer, and J. Chipman, Remote Sensing and Image Interpretation. New York, NY, USA: Wiley, 2008.
3. G. Shaw and D. Manolakis, "Signal processing for hyperspectral image exploitation," IEEE Signal Process. Mag., vol. 50, no. 1, pp. 12-16, Jan. 2002.
4. G. Camps-Valls, D. Tuia, L. Bruzzone, and J. Atli Benediktsson, "Advances in hyperspectral image classification: Earth monitoring with statistical learning methods," IEEE Signal Process. Mag., vol. 31, no. 1, pp. 45-54, Jan. 2014.
5. G. Camps-Valls, D. Tuia, L. Gómez-Chova, S. Jiménez, and J. Malo, Eds. Remote Sensing Image Processing. Laporte, CO, USA: Morgan & Claypool, Sep. 2011.
6. R. Willett, M. Duarte, M. Davenport, and R. Baraniuk, "Sparsity and structure in hyperspectral imaging: Sensing, reconstruction, and target detection," IEEE Signal Process. Mag., vol. 31, no. 1, pp. 116-126, Jan. 2014.
7. W.-K. Ma et al., "A signal processing perspective on hyperspectral unmixing: Insights from remote sensing," IEEE Signal Process. Mag., vol. 31, no. 1, pp. 67-81, Jan. 2014.
8. G. Arce, D. Brady, L. Carin, H. Arguello, and D. Kittle, "Compressive coded aperture spectral imaging: An introduction," IEEE Signal Process. Mag., vol. 31, no. 1, pp. 105-115, Jan. 2014.
9. D. Roy et al., "Landsat-8: Science and product vision for terrestrial global change research," Remote Sens. Environ., vol. 145, no. 0, pp. 154-172, Apr. 2014.
10. N. Longbotham, F. Pacifici, B. Baugh, and G. Camps-Valls, "Prelaunch assessment of worldview-3 information content," in Proc. WHISPERS, Lausanne, Switzerland, 2014, pp. 479-486.
11. M. Drusch et al., "Sentinel-2: ESA's optical high-resolution mission for GMES operational services," Remote Sens. Environ., vol. 120, pp. 25-36, May 2012.
12. C. Donlon et al., "The Global Monitoring for Environment and Security (GMES) sentinel-3 mission," Remote Sens. Environ., vol. 120, pp. 37-57, May 2012.
13. T. Stuffler et al., "The EnMAP hyperspectral imager-An advanced optical payload for future applications in Earth observation programmes," Acta Astronaut., vol. 61, no. 1-6, pp. 115-120, Aug. 2007.
14. D. Roberts, D. Quattrochi, G. Hulley, S. Hook, and R. Green, "Synergies between VSWIR and TIR data for the urban environment: An evaluation of the potential for the Hyperspectral Infrared Imager (HyspIRI) decadal survey mission," Remote Sens. Environ., vol. 117, pp. 83-101, Feb. 2012.
15. S. Kraft, U. Del Bello, M. Bouvet, M. Drusch, and J. Moreno, "Flex: ESA'S Earth explorer 8 candidate mission," in Proc. IEEE IGARSS, 2012, pp. 7125-7128.
16. G. Camps-Valls and L. Bruzzone, "Kernel-based methods for hyperspec-tral image classification," IEEE Trans. Geosci. Remote Sens., vol. 43, no. 6, pp. 1351-1362, Jun. 2005.
17. G. Camps-Valls and L. Bruzzone, Eds. Kernel Methods for Remote Sensing Data Analysis. Chichester, U.K.: Wiley, Dec. 2009.
18. I. Jolliffe, Principal Component Analysis. Berlin, Germany: Springer-Verlag, 2002.
19. J. A. Lee and M. Verleysen, Nonlinear Dimensionality Reduction. Berlin, Germany: Springer-Verlag, 2007.
20. C. Bachmann, T. Ainsworth, and R. Fusina, "Improved manifold coordinate representations of large-scale hyperspectral scenes," IEEE Trans. Geosci. Remote Sens., vol. 44, no. 10, pp. 2786-2803, Oct. 2006.
21. J. Arenas-García, K. B. Petersen, G. Camps-Valls, and L. K. Hansen, "Kernel multivariate analysis framework for supervised subspace learning: A tutorial on linear and kernel multivariate methods," IEEE Signal Process. Mag., vol. 30, no. 4, pp. 16-29, Jul. 2013.
22. G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, vol. 313, no. 5786, pp. 504-507, Jul. 2006.
23. V. Laparra, G. Camps, and J. Malo, "Iterative Gaussianization: From ICA to random rotations," IEEE Trans. Neural Netw., vol. 22, no. 4, pp. 537-549, Apr. 2011.
24. A. Baraldi and F. Parmiggiani, "A neural network for unsupervised categorization of multivalued input patterns: An application to satellite image clustering," IEEE Trans. Geosci. Remote Sens., vol. 33, no. 2, pp. 305-316, Mar. 1995.
25. S. Ghosh, L. Bruzzone, S. Patra, F. Bovolo, and A. Ghosh, "A context-sensitive technique for unsupervised change detection based on Hopfield-type neural networks," IEEE Trans. Geosci. Remote Sens., vol. 45, no. 3, pp. 778-789, Mar. 2007.
26. F. Del Frate, G. Licciardi, and R. Duca, "Autoassociative neural networks for features reduction of hyperspectral data," in Proc. IEEE 1st WHISPERS, Aug. 2009, pp. 1-4.
27. G. Licciardi, F. Del Frate, and R. Duca, "Feature reduction of hyperspec-tral data using autoassociative neural networks algorithms," in Proc. IEEE IGARSS, Jul. 2009, vol. 1, pp. I-176-I-179.
28. C. Vaduva, I. Gavat, and M. Datcu, "Deep learning in very high resolution remote sensing image information mining communication concept," in Proc. IEEE 20th EUSIPCO, Aug. 2012, pp. 2506-2510.
29. V. Mnih and G. Hinton, "Learning to label aerial images from noisy data," in Proc. 29th ICML, 2012, pp. 567-574.
30. X. Chen, S. Xiang, C.-L. Liu, and C.-H. Pan, "Vehicle detection in satellite images by hybrid deep convolutional neural networks," IEEE Geosci. Remote Sens. Lett., vol. 11, no. 10, pp. 1797-1801, Oct. 2014.
31. Y. Chen, Z. Lin, X. Zhao, G. Wang, and Y. Gu, "Deep learning-based classification of hyperspectral data," IEEE J. Sel. Topics Appl. Earth Observ., vol. 7, no. 6, pp. 2094-2107, Jun. 2014.
32. Z. Wang, N. Nasrabadi, and T. Huang, "Spatial-spectral classification of hyperspectral images using discriminative dictionary designed by learning vector quantization," IEEE Trans. Geosci. Remote Sens., vol. 52, no. 8, pp. 4808-4822, Aug. 2014.
33. S. Yang, H. Jin, M. Wang, Y. Ren, and L. Jiao, "Data-driven compressive sampling and learning sparse coding for hyperspectral image classification," IEEE Geosci. Remote Sens. Lett., vol. 11, no. 2, pp. 479-483, Feb. 2014.
34. S. Li, H. Yin, and L. Fang, "Remote sensing image fusion via sparse representations over learned dictionaries," IEEE Trans. Geosci. Remote Sens., vol. 51, no. 9, pp. 4779-4789, Sep. 2013.
35. D. Dai and W. Yang, "Satellite image classification via two-layer sparse coding with biased image representation," IEEE Geosci. Remote Sens. Lett., vol. 8, no. 1, pp. 173-176, Jan. 2011.
36. I. Rigas, G. Economou, and S. Fotopoulos, "Low-level visual saliency with application on aerial imagery," IEEE Geosci. Remote Sens. Lett., vol. 10, no. 6, pp. 1389-1393, Nov. 2013.
37. H. Sun, X. Sun, H. Wang, Y. Li, and X. Li, "Automatic target detection in high-resolution remote sensing images using spatial sparse coding bag-of-words model," IEEE Geosci. Remote Sens. Lett., vol. 9, no. 1, pp. 109-113, Jan. 2012.
38. A. Cheriyadat, "Unsupervised feature learning for aerial scene classification," IEEE Trans. Geosci. Remote Sens., vol. 52, no. 1, pp. 439-451, Jan. 2014.
39. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," in Intelligent Signal Processing, S. Haykin and B. Kosko, Eds. Piscataway, NJ, USA: IEEE Press, 2001, pp. 306-351. [Online]. Available: http://yann.lecun.com/exdb/publis/pdf/ lecun-01a.pdf
40. G. E. Hinton, S. Osindero, and Y.-W. Teh, "A fast learning algorithm for deep belief nets," Neural Comput., vol. 18, no. 7, pp. 1527-1554, Jul. 2006.
41. Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, "Greedy layerwise training of deep networks," in Proc. NIPS, 2006, pp. 153-160.
42. H. Lee, R. Grosse, R. Ranganath, and A. Y. Ng, "Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations," in Proc. 26th Annu. ICML, New York, NY, USA, 2009, pp. 609-616.
43. J. Masci, U. Meier, D. Cireşan, and J. Schmidhuber, "Stacked convo-lutional auto-encoders for hierarchical feature extraction," in Proc. 21st ICANN, Berlin, Germany, 2011, pp. 52-59.
44. A. Romero, P. Radeva, and C. Gatta, "Meta-parameter free unsupervised sparse feature learning," IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 8, pp. 1716-1722, Aug. 2015.
45. Y. LeCun, L. Bottou, G. Orr, and K. Müller, "Efficient backprop," in Neural Networks: Tricks of the Trade. Berlin, Germany, Springer-Verlag, 1998, pp. 9-50.
46. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Proc. Adv. Neural Inf. Process. Syst., 2012, pp. 1097-1105.
47. P. Sermanet et al., "Overfeat: Integrated recognition, localization and detection using convolutional networks," in Proc. ICLR, Apr. 2014, pp. 1-16.
48. J. Ngiam, P. W. Koh, Z. Chen, S. Bhaskar, and A. Y. Ng, "Sparse filtering," in Proc. NIPS, 2011, pp. 1125-1133.
49. K. Kavukcuoglu et al., "Learning convolutional feature hierarchies for visual recognition," in Proc. NIPS, 2010, pp. 1090-1098.
50. Y. Bengio, A. C. Courville, and P. Vincent, "Representation learning: A review and new perspectives," IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 8, pp. 1798-1828, Aug. 2013.
51. D. J. Field, "What is the goal of sensory coding?" Neural Comput., vol. 6, no. 4, pp. 559-601, Jul. 1994.
52. B. Olshausen and D. J. Field, "Sparse coding with an overcomplete basis set: A strategy employed by V1?" Vis. Res., vol. 37, no. 23, pp. 3311-3325, 1997.
53. M. A. Ranzato, C. Poultney, S. Chopra, and Y. Lecun, "Efficient learning of sparse representations with an energy-based model," in Proc. NIPS, 2006, pp. 1137-1144.
54. B. Willmore and D. J. Tolhurst, "Characterizing the sparseness of neural codes," Network, vol. 12, no. 12, pp. 255-270, Aug. 2001.
55. A. Coates and A. Ng, "The importance of encoding versus training with sparse coding and vector quantization," in Proc. ICML, 2011, pp. 921-928.
56. T. Schaul, S. Zhang, and Y. LeCun, "No more pesky learning rates," in Proc. ICML, 2013, pp. 1-7.
57. Y. Yang and S. Newsam, "Bag-of-visual-words and spatial extensions for land-use classification," in Proc. GIS, San Jose, CA, USA, 2010, pp. 270-279.
58. A. C. Hill, T. S. Bansak, B. K. Ellis, and J. A. Stanford, "Merits and limits of ecosystem protection for conserving wild salmon in a northern coastal British Columbia river," Ecol. Soc., vol. 15, no. 2, pp. 1-20, 2010.
59. D. C. Whited, J. S. Kimball, M. Lorang, and J. Stanford, "Estimation of juvenile salmon habitat in pacific rim rivers using multiscalar remote sensing and geospatial analysis," River Res. Appl., vol. 29, no. 2, pp. 135-148, Feb. 2013.
60. B. Tian, M. Shaikh, M. Azimi-Sadjadi, T. Haar, and D. Reinke, "A study of cloud classification with neural networks using spectral and textural features," IEEE Trans. Neural Netw., vol. 10, no. 1, pp. 138-151, Jan. 1999.
61. T. McIntire and J. Simpson, "Arctic sea ice, cloud, water, and lead classification using neural networks and 1.6-μm data," IEEE Trans. Geosci. Remote Sens., vol. 40, no. 9, pp. 1956-1972, Sep. 2002.
62. J. Arriaza, F. Rojas, M. López, and M. Cantón, "An automatic cloudmask-ing system using backpro neural nets for AVHRR scenes," IEEE Trans. Geosci. Remote Sens., vol. 41, no. 4, pp. 826-831, Apr. 2003.
63. L. Gómez-Chova, G. Camps-Valls, L. Bruzzone, and J. Calpe-Maravilla, "Mean map kernel methods for semisupervised cloud classification," IEEE Trans. Geosci. Remote Sens., vol. 48, no. 1, pp. 207-220, Jan. 2010.
64. L. Gómez-Chova, G. Camps-Valls, J. Muñoz-Marí, and J. Calpe, "Semi-supervised image classification with Laplacian support vector machines," IEEE Geosci. Remote Sens. Lett., vol. 5, no. 4, pp. 336-340, Jul. 2008.
65. L. Gómez-Chova, G. Camps-Valls, J. Calpe, L. Guanter, and J. Moreno, "Cloud-screening algorithm for ENVISAT/MERIS multispectral images," IEEE Trans. Geosci. Remote Sens., vol. 45, no. 12, pp. 4105-4118, Dec. 2007.
66. F. García-Vílchez et al. and, "On the impact of lossy compression on hyperspectral image classification and unmixing," IEEE Geosci. Remote Sens. Lett., vol. 8, no. 2, pp. 253-257, Mar. 2011.
67. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: A simple way to prevent neural networks from overfitting," J. Mach. Learning Res., vol. 15, pp. 1929-1958, 2014.