A Markov random field model for classification of multisource satellite imagery

A general model for multisource classification of remotely sensed data based on Markov random fields (MRF) is proposed. A specific model for fusion of optical images, synthetic aperture radar (SAR) images, and GIS (geographic information systems) ground cover data is presented in detail and tested. The MRF model exploits spatial class dependencies (spatial context) between neighboring pixels in an image, and temporal class dependencies between different images of the same scene. By including the temporal aspect of the data, the proposed model is suitable for detection of class changes between the acquisition dates of different images. The performance of the proposed model is investigated by fusing Landsat TM images, multitemporal ERS-1 SAR images, and GIS ground-cover maps for land-use classification, and on agricultural crop classification based on Landsat TM images, multipolarization SAR images, and GIS crop field border maps. The performance of the MRF model is compared to a simpler reference fusion model. On an average, the MRF model results in slightly higher (2%) classification accuracy when the same data is used as input to the two models. When GIS field border data is included in the MRF model, the classification accuracy of the MRF model improves by 8%. For change detection in agricultural areas, 75% of the actual class changes are detected by the MRF model, compared to 62% for the reference model. Based on the well-founded theoretical basis of Markov random field models for classification tasks and the encouraging experimental results in our small-scale study, the authors conclude that the proposed MRF model is useful for classification of multisource satellite imagery.

[1]  Rama Chellappa,et al.  Segmentation of synthetic-aperture-radar complex data , 1991 .

[2]  R. Chellappa,et al.  Lognormal random field models and their applications to radar image synthesis , 1987, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Malcolm C. Harrison,et al.  An analysis of four uncertainty calculi , 1988, IEEE Trans. Syst. Man Cybern..

[4]  Anil K. Jain,et al.  Texture Analysis , 2018, Handbook of Image Processing and Computer Vision.

[5]  Jong-Sen Lee,et al.  Speckle analysis and smoothing of synthetic aperture radar images , 1981 .

[6]  N. Khazenie,et al.  Spatial-temporal Autocorrelated Model For Contextual Classification , 1990 .

[7]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[8]  Jon Atli Benediktsson,et al.  a Method of Statistical Multisource Classification with a Mechanism to We!ght the Influence of the Data Sources , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.

[9]  P. H. Swain,et al.  Bayesian classification in a time-varying environment , 1978 .

[10]  L. Janssen,et al.  Implementation of temporal relationships in knowledge based classification of satellite images. , 1991 .

[11]  Steven E. Franklin,et al.  Ancillary data input to satellite remote sensing of complex terrain phenomena , 1989 .

[12]  D.A. Landgrebe,et al.  Classification with spatio-temporal interpixel class dependency contexts , 1992, IEEE Trans. Geosci. Remote. Sens..

[13]  Olivier D. Faugeras,et al.  Building, Registrating, and Fusing Noisy Visual Maps , 1988, Int. J. Robotics Res..

[14]  H. Derin,et al.  Modeling and segmentation of speckled images using complex data , 1990 .

[15]  Josef Raviv,et al.  Decision making in Markov chains applied to the problem of pattern recognition , 1967, IEEE Trans. Inf. Theory.

[16]  H. Tjelmeland,et al.  Speckle Reduction and Maximum Likelihood Classification of Sar Images from Sea Ice Recorded During Mizex 87 , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.

[17]  Josef Kittler,et al.  Contextual classification of multispectral pixel data , 1984, Image Vis. Comput..

[18]  Anil K. Jain,et al.  Markov random fields : theory and application , 1993 .

[19]  Mongi A. Abidi,et al.  Data fusion in robotics and machine intelligence , 1992 .

[20]  Anil K. Jain,et al.  Texture Analysis in the Presence of Speckle Noise , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[21]  David A. Landgrebe,et al.  A means for utilizing ancillary information in multispectral classification. [of remotely sensed data , 1982 .

[22]  John Haslett,et al.  Maximum likelihood discriminant analysis on the plane using a Markovian model of spatial context , 1985, Pattern Recognit..

[23]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Christopher C. Wackerman,et al.  The modified beta density function as a model for synthetic aperture radar clutter statistics , 1991, IEEE Trans. Geosci. Remote. Sens..

[25]  Anil K. Jain,et al.  Random field models in image analysis , 1989 .

[26]  Jan P. Allebach,et al.  Combating Speckle In SAR Images: Vector Filtering And Sequential Classification Based On A Multiplicative Noise Model , 1990 .

[27]  Robert M. Haralick,et al.  Decision Making in Context , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Oleg G. Jakubowicz.  Autonomous Reconfiguration Of Sensor Systems Using Neural Nets , 1988, Defense, Security, and Sensing.

[29]  P. Swain,et al.  Neural Network Approaches Versus Statistical Methods In Classification Of Multisource Remote Sensing Data , 1990 .

[30]  John M. Richardson,et al.  Fusion of Multisensor Data , 1988, Int. J. Robotics Res..

[31]  R. Chellappa,et al.  SEGMENTATION OF SYNTHETIC APERTURE RADAR COMPLEX DATA , 1990, 1990 Conference Record Twenty-Fourth Asilomar Conference on Signals, Systems and Computers, 1990..

[32]  W. A. Wright.  A Markov random field approach to data fusion and colour segmentation , 1989, Image Vis. Comput..

[33]  Anil K. Jain,et al.  Multisource classification of remotely sensed data: fusion of Landsat TM and SAR images , 1994, IEEE Trans. Geosci. Remote. Sens..

[34]  Rama Chellappa,et al.  Segmentation of polarimetric synthetic aperture radar data , 1992, IEEE Trans. Image Process..

[35]  P. Swain,et al.  A method for classification of multisource data using interval-valued probabilities and its application to HIRIS data , 1990 .

[36]  Jong-Sen Lee,et al.  Intensity and phase statistics of multi-look polarimetric SAR imagery , 1993, Proceedings of IGARSS '93 - IEEE International Geoscience and Remote Sensing Symposium.

[37]  B. Jeon,et al.  Spatio-temporal contextual classification of remotely sensed multispectral data , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[38]  Godfried T. Toussaint,et al.  The use of context in pattern recognition , 1978, Pattern Recognit..

[39]  Tomaso Poggio,et al.  Probabilistic Solution of Ill-Posed Problems in Computational Vision , 1987 .

[40]  Tong Lee,et al.  Probabilistic and Evidential Approaches for Multisource Data Analysis , 1987, IEEE Transactions on Geoscience and Remote Sensing.

[41]  D. Leckie.  Synergism of synthetic aperture radar and visible/infrared data for forest type discrimination. , 1990 .