The integration of spatial context information in an experimental knowledge-based system and the supervised relaxation algorithm : two successful approaches to improving SPOT-XS classification

Abstract This paper describes two different methods which integrate contextual information in a classification process. This process aims to refine the map products given by the application of a common parametric classification algorithm. The first method is the well known Supervised Relaxation Algorithm, and makes use of the first classification, with additional contextual information. The contextual information is derived either from texture features or from other map products introducing additional information on the existing land use classes. The second method is a knowledge-based system, which makes use of image and geographical context rules. The probability figures, derived from the image classifier and the rule base are combined by the use of the Dempster-Shafer reasoning scheme. Experiments using satellite data from the Loir et Cher region (Central France), together with the appropriate ground truth data, have shown that both methods return improved classification products in terms of thematic an...

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

[2]  D. Civco.  Topographic normalization of landsat thematic mapper digital imagery , 1989 .

[3]  Edward H. Shortliffe,et al.  A Method for Managing Evidential Reasoning in a Hierarchical Hypothesis Space , 1985, Artif. Intell..

[4]  Sidney Marks,et al.  Discriminant Functions When Covariance Matrices are Unequal , 1974 .

[5]  J. A. Richards,et al.  Pixel Labeling by Supervised Probabilistic Relaxation , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Olivier D. Faugeras,et al.  Decorrelation Methods of Texture Feature Extraction , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  W. Cibula,et al.  Use of topographic and climatological models in a geographical data base to improve Landsat MSS classification for Olympic National Park , 1987 .

[8]  E. S. Gilbert,et al.  The effect of unequal variance-covariance matrices on Fisher's linear discriminant function. , 1969, Biometrics.

[9]  Andrew K. Skidmore,et al.  Forest mapping accuracies are improved using a supervised nonparametric classifier with SPOT data , 1988 .

[10]  J. W. Merchant,et al.  Using spatial logic in classification of Landsat TM data , 1984 .

[11]  D. Peddle,et al.  Image texture processing and data integration for surface pattern discrimination , 1991 .

[12]  C. Harlow,et al.  Computational image interpretation models : an overview and a perspective , 1990 .

[13]  A. Jones,et al.  Use of digital terrain data in the interpretation of SPOT-1 HRV multispectral imagery , 1988 .

[14]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[15]  Azriel Rosenfeld,et al.  A Comparative Study of Texture Measures for Terrain Classification , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[16]  T. Logan,et al.  Improving forest cover classification accuracy from Landsat by incorporating topographic information , 1978 .

[17]  V. K. Shettigara,et al.  Robustness of Gaussian Maximum Likelihood and Linear Discriminant Classifiers , 1991, [Proceedings] IGARSS'91 Remote Sensing: Global Monitoring for Earth Management.

[18]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[19]  D. F. Morrison,et al.  Multivariate Statistical Methods , 1968 .

[20]  A. Skidmore.  An expert system classifies eucalypt forest types using thematic mapper data and a digital terrain model , 1989 .