[1]YAO Futian,QIAN Yuntao.Gaussian process and its applications in hyperspectral image classification[J].CAAI Transactions on Intelligent Systems,2011,6(5):396-404.
Copy

Gaussian process and its applications in hyperspectral image classification

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 6 Number of periods: 2011 5 Page number: 396-404 Column: 学术论文—人工智能基础 Public date: 2011-10-30
Title:
Gaussian process and its applications in hyperspectral image classification
Author(s):
YAO Futian1; 2;  QIAN Yuntao1; 2
1.College of Computer Science, Zhejiang University, Hangzhou 310027, China;
2.Institute of Artificial Intelligence, Zhejiang University, Hangzhou 310027, China
Keywords:
Gaussian process;  hyperspectral imaging;  machine learning;  image classification
CLC:
TP181
DOI:
-
Abstract:
Hyperspectral image classification is one of the hotspots in the field of remote sensing applications. The classification performance is affected by the inherit characteristics of hyperspectral imaging. Gaussian process (GP) is a recently developed machine learning method which enables explicitly probabilistic modeling and makes results easily interpretable. Furthermore, hyperparameters of GP can be learned from training data, which overcomes the difficulties of fixing model parameters in most classifiers. This paper introduced the basic concept of GP and some GPbased classification methods. After analyzing the characteristics of hyperspectral imaging and the existing classification methods for hyperspectral images, GP based classification for hyperspectral images was discussed, and some new GPbased classification methods such as GP with spatial constraints and semisupervised GP methods were proposed. Finally, several future research trends of GP and hyperspectral image classification were given.
References:
［1］WIENER N. Extrapolation, interpolation, and smoothing of stationary time series, with engineering applications［M］. Cambridge, USA: MIT Press, 1949: 102106.
［2］MATHERON G. The intrinsic random functions and their applications［J］. Advances in Applied Probability, 1973, 5(3): 439468.
［3］JOURNEL A G, HUIJBREGTS C J. Mining geostatistics［M］. New York, USA: SpringerVerlag, 1978: 304310.
［4］THOMPSON P D. Optimum smoothing of twodimensional fields［J］. Tellus, 1956, 8(3): 384393.
［5］DALEY R. Atmospheric data analysis［M］. Cambridge, UK: Cambridge University Press, 1993: 99107.
［6］WHITTLE P. Prediction and regulation by linear leastsquare methods［M］. London, UK: English Universities Press, 1984: 5869.
［7］RIPLEY B D. Spatial statistics［M］. Hoboken, USA: WileyIEEE, 2004: 4450.
［8］CRESSIE N. Statistics for spatial data［J］. Terra Nova, 1992, 4(5): 613617.
［9］O’HAGAN A, KINGMAN J F C. Curve fitting and optimal design for prediction［J］. Journal of the Royal Statistical Society: Series B (Methodological), 1978, 40(1): 142.
［10］SACKS J, WELCH W J, MITCHELL T J, et al. Design and analysis of computer experiments［J］. Statistical Science, 1989, 4(4): 409423.
［11］SANTNER T J, WILLIAMS B J, NOTZ W. The design and analysis of computer experiments［M］. New York, USA: SpringerVerlag, 2003: 61 65.
［12］WILLIAMS C K I, RASMUSSEN C E. Gaussian processes for regression［M］. Cambridge, USA: MIT Press, 1996: 2537.
［13］RASMUSSEN C E, WILLIAMS C K. Gaussian processes for machine learning［M］. Cambridge, USA: MIT Press, 2006: 1530.
［14］WILLIAMS C K I, BARBER D. Bayesian classification with Gaussian processes［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(12): 13421351.
［15］GIBBS M N, MACKAY D J C. Variational Gaussian process classifiers［J］. IEEE Transactions on Neural Networks, 2000, 11(6): 14581464.
［16］NEAL R. Regression and classification using Gaussian process priors［J］. Bayesian Statistics, 1998, 6(10): 475501.
［17］CHANG C I. Hyperspectral imaging: techniques for spectral detection and classification［M］. New York, USA: Kluwer Academic Plenum Publishers, 2003: 816.
［18］MINKA T P. A family of algorithms for approximate Bayesian inference［D］. Cambridge: Massachusetts Institute of Technology, 2001: 3648.
［19］GIBBS M N, MACKAY D J C. Variational Gaussian process classifiers［J］. IEEE Transactions on Neural Networks, 2002, 11(6): 14581464.
［20］SEEGER M. Bayesian model selection for support vector machines, Gaussian processes and other kernel classifiers ［M］//SOLLA S A, LEEN T K, MULLER K L. Advances in Neural Information Processing Systems. Cambridge, USA: the MIT Press, 2000: 603609.
［21］SHAWETAYLOR J, CRISTIANINI N. Kernel methods for pattern analysis［M］. Cambridge, UK: Cambridge University Press, 2004: 4857.
［22］FLETCHER R. Practical methods of optimization: constrained optimization［M］. Hoboken, USA: John Wiley & Sons Inc, 1984: 8794.
［23］NOCEDAL J, WRIGHT S J. Numerical optimization［M］. New York, USA: SpringerVerlag, 1999: 5364.
［24］URTASUN R, DARRELL T. Discriminative Gaussian process latent variable model for classification［C］//International Conference on Machine Learning. Corvallis, USA, 2007: 934937.
［25］BAUDAT G, ANOUAR F. Generalized discriminant analysis using a kernel approach［J］. Neural Computation, 2000, 12(10): 23852404.
［26］SUGIYAMA M. Local Fisher discriminant analysis for supervised dimensionality reduction［C］//International Conference on Machine Learning. Pittsburgh, USA, 2006: 905912.
［27］GROCHOW K, MARTIN S L, HERTZMANN A, et al. Stylebased inverse kinematics［J］. ACM Transactions on Graphics, 2004, 23(3): 522531.
［28］CSAT L. Gaussian processes: iterative sparse approximation［D］. Birmingham, UK: Aston University, 2005: 2634.
［29］ZHU Xiaojin, GHAHRAMANI Z, LAFFERTY J. Semisupervised learning using Gaussian fields and harmonic functions［C］//Proceedings of the 20th International Conference on Machine Learning. Washington, DC, USA, 2003: 912914.
［30］SINDHWANI V, CHU W, KEERTHI S S. Semisupervised Gaussian process classifiers［C］//International Joint Conference on Artificial Intelligence. Hyderabad, India, 2007: 10591064.
［31］HUGHES G. On the mean accuracy of statistical pattern recognizers［J］. IEEE Transactions on Information Theory, 1968, 14(1): 5563.
［32］QIAN Y, YAO F, JIA S. Band selection for hyperspectral imagery using affinity propagation［J］. IET Computer Vision, 2010, 3(4): 213222.
［33］贺霖,潘泉,邸韦华,等.高光谱图像高维多尺度自回归有监督检测［J］. 自动化学报, 2009, 35(5): 509518. HE Lin, PAN Quan, DI Weihua, et al. Supervised detection for hyperspectral imagery based on high dimensional multiscale autoregression［J］. Acta Automatica Sinica, 2009, 35(5): 509518.
［34］熊桢，童庆禧.用于高光谱遥感图象分类的一种高阶神经网络算法［J］. 中国图象图形学报, 2000, 5(3): 196201.
XIONG Zhen, TONG Qingxi. Highrank artificial neural network algorithm for classification of hyperspectral image data［J］. Journal of Image and Graphics, 2000, 5(3): 196201.
［35］MELGANI F, BRUZZONE L. Classification of hyperspectral remote sensing images with support vector machines［J］. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(8): 17781790.
［36］刘春红.超光谱遥感图像降维及分类方法研究［D］.哈尔滨：哈尔滨工程大学, 2005: 8694.
LIU Chunhong. Research on dimensional reduction and classification of hyperspectral remote sensing image［D］. Harbin: Harbin Engineering University, 2005: 8694.
［37］KITTLER J, PAIRMAN D. Contextual pattern recognition applied to cloud detection and identification［J］. IEEE Transactions on Geoscience and Remote Sensing, 2007, 23(6): 855863.
［38］姚伏天,钱沄涛.用于高光谱遥感图像分类的空间约束高斯过程方法［J］.南京大学学报:自然科学版, 2009, 45(5): 665670.
?YAO Futian, QIAN Yuntao. A spatial Gaussian process method for hyperspectral remote sensing imagery classification［J］. Journal of Nanjing University: Natural Sciences, 2009, 45(5): 665670.
［39］ROSSI R E, DUNGAN J L, BECK L R. Kriging in the shadows: geostatistical interpolation for remote sensing［J］. Remote Sensing of Environment, 1994, 49(1): 3240.
［40］DENG H, CLAUSI D A. Advanced Gaussian MRF rotationinvariant texture features for classification of remote sensing imagery［C］//Computer Society Conference on Computer Vision and Pattern Recognition. Madison, USA, 2003: 685689.
［41］ZHONG Ping, WANG Runsheng. A multiple conditional random fields ensemble model for urban area detection in remote sensing optical images［J］. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12): 39783988.
［42］LAFFERTY J, MCCALLUM A, PEREIRA F. Conditional random fields: probabilistic models for segmenting and labeling sequence data［C］//Proceedings of the Eighteenth International Conference on Machine Learning. Williamstown, USA, 2001: 282289.
［43］KUMAR S, HEBERT M. Discriminative random fields［J］. International Journal of Computer Vision, 2006, 68(2): 179201.
［44］LI Jiming, HU Zhenfang, QIAN Yuntao. Hyperspectral data classification using margin infused relaxed algorithm［C］//International Conference on Image Processing. Hong Kong, China, 2009: 16691672.
［45］LI Jiming, QIAN Yuntao. Regularized multinomial regression method for hyperspectral data classification via pathwise coordinate optimization［C］//Digital Image Computing: Techniques and Applications. Melbourne, Australia, 2009: 540545.
［46］YAO Futian, Qian Yuntao. Band selection based Gaussian processes for hyperspectral remote sensing images classification［C］//International Conference on Image Processing. Hong Kong, China, 2009: 28452848.
［47］VATSAVAI R R, SHEKHAR S, BURK T E. A semisupervised learning method for remote sensing data mining［C］//International Conference on Tools with Artificial Intelligence. Hong Kong, China, 2005: 205211.
［48］BELKIN M, NIYOGI P, SINDHWANI V. Manifold regularization: a geometric framework for learning from labeled and unlabeled examples［J］. The Journal of Machine Learning Research, 2006, 7: 23992434.
Similar References:

Memo

-

Last Update: 2011-11-16

Copyright © CAAI Transactions on Intelligent Systems