An optimal multiedge detector for SAR image segmentation

Edge detection is a fundamental issue in image analysis. Due to the presence of speckle, which can be modeled as a strong, multiplicative noise, edge detection in synthetic aperture radar (SAR) images is extremely difficult, and edge detectors developed for optical images are inefficient. Several robust operators have been developed for the detection of isolated step edges in speckled images. The authors propose a new step-edge detector for SAR images, which is optimal in the minimum mean square error (MSSE) sense under a stochastic multiedge model. It computes a normalized ratio of exponentially weighted averages (ROEWA) on opposite sides of the central pixel. This is done in the horizontal and vertical direction, and the magnitude of the two components yields an edge strength map. Thresholding of the edge strength map by a modified version of the watershed algorithm and region merging to eliminate false edges complete an efficient segmentation scheme. Experimental results obtained from simulated SAR images as well as ERS-1 data are presented.

[1]  A. Lopes,et al.  Different approaches to multiedge detection in SAR images , 1997, IGARSS'97. 1997 IEEE International Geoscience and Remote Sensing Symposium Proceedings. Remote Sensing - A Scientific Vision for Sustainable Development.

[2]  D. M. Smith,et al.  Speckle reduction and segmentation of Synthetic Aperture Radar images , 1996 .

[3]  Jun Shen,et al.  An optimal linear operator for step edge detection , 1992, CVGIP Graph. Model. Image Process..

[4]  Rod Cook,et al.  Segmentation and simulated annealing , 1996, Remote Sensing.

[5]  Victor S. Frost,et al.  Edge detection for synthetic aperture radar and other noisy images , 1982 .

[6]  J. Stern,et al.  Méthodes pratiques d'étude des fonctions aléatoires , 1967 .

[7]  Victor S. Frost,et al.  A Model for Radar Images and Its Application to Adaptive Digital Filtering of Multiplicative Noise , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  R. G. White,et al.  Change detection in SAR imagery , 1990 .

[9]  C. Swift,et al.  Microwave remote sensing , 1980, IEEE Antennas and Propagation Society Newsletter.

[10]  Laurent Najman,et al.  Geodesic Saliency of Watershed Contours and Hierarchical Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Rod Cook,et al.  MUM (Merge Using Moments) segmentation for SAR images , 1994, Remote Sensing.

[12]  Alan C. Bovik,et al.  On detecting edges in speckle imagery , 1988, IEEE Trans. Acoust. Speech Signal Process..

[13]  F. Parmiggiani,et al.  Segmentation driven by an iterative pairwise mutually best merge criterion , 1995, 1995 International Geoscience and Remote Sensing Symposium, IGARSS '95. Quantitative Remote Sensing for Science and Applications.

[14]  John W. Woods,et al.  Comments on "A Model for Radar Images and Its Application to Adaptive Digital Filtering of Multiplicative Noise" , 1984, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Philippe Marthon,et al.  Finding the structure of a satellite image , 1994, Remote Sensing.

[16]  Armand Lopes,et al.  Multisource classification of SAR images with the use of segmentation, polarimetry, texture, and multitemporal data , 1996, Remote Sensing.

[17]  A. Lopes,et al.  A statistical and geometrical edge detector for SAR images , 1988 .

[18]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[19]  Michel Grimaud,et al.  New measure of contrast: the dynamics , 1992, Optics & Photonics.

[20]  C. Oliver,et al.  Optimum edge detection in SAR , 1996 .

[21]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..