Segmenting multispectral Landsat TM images into field units

Presents a procedure for the automated segmentation of multispectral Landsat TM images of farmland in Western Australia into field units. The segmentation procedure, named the canonically-guided region growing (CGRG) procedure, assumes that each field contains only one ground cover type and that the width of the minimum field of interest is known. The CGRG procedure segments images using a seeded region growing algorithm, but is novel in the method used to generate the internal field markers used as "seeds." These internal field markers are obtained from a multiband, local canonical eigenvalue image. Before the local transformation is applied, the original image is morphologically filtered to estimate both between-field variation and within-field variation in the image. Local computation of the canonical variate transform, using a moving window sized to fit just inside the smallest field of interest, ensures that the between- and within-field spatial variations in each image band are accommodated. The eigenvalues of the local transform are then used to discriminate between an area completely inside a field or at a field boundary. The results obtained using CGRG and the methods of Lee (1997) and Tilton (1998) were numerically compared to "ideal" segmentations of a set of sample satellite images. The comparison indicates that the results of the CGRG are usually more accurate in terms of field boundary position and degree of over-segmentation and under-segmentation, than either of the other procedures.

[1]  J. L. Moigne,et al.  Refining image segmentation by integration of edge and region data , 1992, IEEE Trans. Geosci. Remote. Sens..

[2]  C. Ji.  Delineating agricultural field boundaries from TM imagery using dyadic wavelet transforms , 1996 .

[3]  Pierre Soille,et al.  Morphological partitioning of multispectral images , 1996, J. Electronic Imaging.

[4]  James C. Tilton,et al.  Image segmentation by region growing and spectral clustering with a natural convergence criterion , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[5]  Ricardo J. Machado,et al.  A neural system for deforestation monitoring on Landsat images of the Amazon Region , 1994, Int. J. Approx. Reason..

[6]  Jorma Rissanen,et al.  Stochastic Complexity in Statistical Inquiry , 1989, World Scientific Series in Computer Science.

[7]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[8]  Martien Molenaar,et al.  Terrain objects, their dynamics and their monitoring by the integration of GIS and remote sensing , 1995, IEEE Trans. Geosci. Remote. Sens..

[9]  Mauro Barni,et al.  THE USE OF DIFFERENT METRICS IN VECTOR MEDIAN FILTERING: APPLICATION TO FINE ARTS AND PAINTINGS , 1992 .

[10]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[11]  J. B. Lee,et al.  Enhancement of high spectral resolution remote-sensing data by a noise-adjusted principal components transform , 1990 .

[12]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .

[14]  P J Rousseeuw,et al.  On the calculation of a robust S-estimator of a covariance matrix. , 1998, Statistics in medicine.

[15]  Agustin Lobo,et al.  Image segmentation and discriminant analysis for the identification of land cover units in ecology , 1997, IEEE Trans. Geosci. Remote. Sens..

[16]  Richard A. Johnson,et al.  Statistics: Principles and Methods , 1985 .

[17]  A. Baddeley.  Errors in binary images and an $Lsp p$ version of the Hausdorff metric , 1992 .

[18]  R. Kettig,et al.  Classification of Multispectral Image Data by Extraction and Classification of Homogeneous Objects , 1976, IEEE Transactions on Geoscience Electronics.