Change Detection of Remote Sensing Images with Semi-supervised Multilayer Perceptron

• Autorzy: Patra S. , Ghosh S. , Ghosh A.
• Języki publikacji: EN

Abstrakty

EN

A context-sensitive change-detection technique based on semi-supervised learning with multilayer perceptron is proposed here. In order to take contextual information into account, input patterns are generated considering each pixel of the difference image along with its neighboring pixels. A heuristic technique is suggested to identify a few initial labeled patterns without using ground truth information. The network is initially trained using these labeled data. The unlabeled patterns are iteratively processed by the already trained perceptron to obtain a soft class label. Experimental results, carried out on two multispectral and multitemporal remote sensing images, confirm the effectiveness of the proposed approach.

Słowa kluczowe

EN

semi-supervised learning; remote sensing; change detection; multitemporal images; neural network

• Wydawca: IOS Press
• Czasopismo: Fundamenta Informaticae
• Rocznik: 2008
• Tom: Vol. 84, nr 3-4
• Strony: 429--442
• Opis fizyczny: bibliogr. 28 poz., fot., wykr.

Twórcy

autor

Patra S.

autor

Ghosh S.

autor

Ghosh A.

• Machine Inteligence Unit Indian Statistical Institute 203, B.T. Road, Kolkata 700 108 India,

Bibliografia

• [1] Alberti, M., Weeks, R., Coe, S.: Urban land cover change analysis in central puget sound, Photogram. Eng. Remote Sensing, 70(9), 2004, 1043-1052.
• [2] Bazi, Y., Bruzzone, L., Melgani, R: An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR images, IEEE Trans. Geosci. Remote Sensing, 43(4), 2005, 874-887.
• [3] Bruzzone, L., Prieto, D. E: Automatic analysis of the difference image for unsupervised change detection, IEEE Trans. Geosci. Remote Sensing, 38(3), 2000, 1171-1182.
• [4] Bruzzone, L., Prieto, D. F.: An adaptive semiparametric and context-based approach to unsupervised change detection in multitemporal remote-sensing images, IEEE Trans. Image Processing, 11(4), 2002,452-466.
• [5] Bruzzone, L., Serpico, S. B.: An iterative technique for the detection of land-cover transitions in multitemporal remote-sensing images, IEEE Trans. Geosci. Remote Sensing, 35(4), 1997, 858-867.
• [6] Chavez, P. S., MacKinnon, D. J.: Automatic detection of vegetation changes in the southwestern United States using remotely sensed images, Photogram. Eng. Remote Sensing, 60(5), 1994,1285-1294.
• [7] Cihlar, J., Pultz, T. J., Gray, A. L.: Change detection with synthetic aperture radar, Int. J. Remote Sensing, 13(3), 1992,401-414.
• [8] Duda, R. O., Hart, P. E., Stork, D. G.: Pattern Classification, Singapore: John Wiley, 2001.
• [9] Fung, T.: An assessment of TM imagery for land-cover change detection, IEEE Trans. Geosci. Remote Sensing, 28(4), 1990,681-684.
• [10] Ghosh, S., Bruzzone, L., Patra, S., Bovolo, F, Ghosh, A.: A context-sensitive technique for unsupervised change detection based on Hopfield-type neural networks, IEEE Trans. Geosci. Remote Sensing, 45(3), 2007, 778-789
• [11] Ghosh, S., Patra, S., Ghosh, A.: A neural approach to unsupervised change detection of remote-sensing images, in: Speech, Audio, Image and Biomedical Signal Processing using Neural Networks (B. Prasad, S. R. M. Prasanna, Eds.), Springer-Verleg, Berlin, 2008, 239-264.
• [12] Gopal, S., Woodcock, C: Remote sensing of forest change using artificial neural networks, IEEE Trans. Geosci. Remote Sensing, 34(2), 1996, 398-404.
• [13] Gosselin, P. H., Cord, M.: Feature-based approach to semi-supervised similarity learning, Pattern Recognition, 39(10), 2006, 1839-1851.
• [14] Hame, T., Heiler, I., Miguel-Ayanz, J. S.: An unsupervised change detection and recognition system for forestry, Int. J. Remote Sensing, 19(6), 1998, 1079-1099.
• [15] Haykin, S.: Neural Networks: A Comprehensive Foundation, Singapore: Pearson Education, Fourth Indian Reprint, 2003.
• [16] Kasetkasem, T., Varshney, P. K.: An image change detection algorithm based on Markov random field models, IEEE Trans. Geosci. Remote Sensing, 40(8), 2002,1815-1823.
• [17] Klir, G. S., Yuan, B.: Fuzzy Sets and Fuzzy Logic - Theory and Applications, Prentice-Hall, Englewood Cliffs, 1995.
• [18] Melgani, F, Moser, G., Serpico, S. B.: Unsupervised change-detection methods for remote sensing data, Opt. Eng., 41,2002,3288-3297.
• [19] Merril, K. R., Jiajun, L.: A comparison of four algorithms for change detection in an urban environment, Remote Sens. Environ., 63(2), 1998, 95-100.
• [20] Miller, D. J., Uyar, H. S.: A mixture of experts classifier with learning based on both labeled and unlabeled data, in: Advances in Neural Information Processing Systems (M. C. Mozer, M. I. Jordan, T. Petsche, Eds.), vol. 9, MIT Press, 1997, 571-577.
• [21] Nigam, K., McCallum, A. K., Thrun, S., Mitchell, T.: Text classification from labeled and unlabeled documents using EM, Machine Learning, 39, 2000, 103-134.
• [22] Patra, S., Ghosh, S., Ghosh, A.: Unsupervised change detection in remote-sensing images using modified self-organizing feature map neural network, Int. Conf. on Computing: Theory and Applications (ICCTA-2007), Kolkata, India, IEEE Computer Society Press, 2007,716-720.
• [23] Radke, R. J., Andra, S., Al-Kofahi, O., Roysam, B.: Image change detection algorithms: A systematic survey, IEEE Trans. Image Processing, 14(3), 2005, 294-307.
• [24] Richards, J. A., Jia, X.: Remote Sensing Digital Image Analysis, 4th ed. Berlin: Springer-Verlag, 2006.
• [25] Seeger, M.: Learning with labeled and unlabeled data, Technical report, University of Edinburgh, 2001.
• [26] Singh, A.: Digital change detection techniques using remotely sensed data, Int. J. Remote Sensing, 10(6), 1989,989-1003.
• [27] Verikas, A., Gelzinis, A., Malmqvist, K.: Using unlabelled data to train a multilayer perceptron, Neural Processing Letters, 14, 2001,179-201.
• [28] Yoon, S. Y., Lee, S. Y.: Training algorithm with incomplete data for feed-forward neural networks, Neural Processing Letters, 10, 1999, 171-179.