Title :
Autocorrelation features for synthetic aperture sonar image seabed segmentation
Author :
Cobb, J. Tory ; Principe, Jose
Author_Institution :
Panama City Div., Naval Surface Warfare Center, Panama City, FL, USA
Abstract :
High-resolution synthetic aperture sonar (SAS) systems yield richly detailed images of seabed environments. Algorithms that automatically segment and label seabed textures such as coral, sea grass, sand ripple, and mud, require suitable features that discriminate between the texture classes. Here we present a robust, parameterized SAS image texture model based on the autocorrelation function (ACF) of the intensity image. This ACF texture model has been shown to accurately model first- and second-order statistical features of various seabed environments. An unsupervised multi-class k-means segmentation algorithm that uses the features derived from the ACF model is employed to label rock and ripple textures from a set of textured SAS images. The results of the segmentation are compared against the performance of the segmentation approach using biorthogonal wavelets and Haralick features. In the described experiments, the ACF model features are shown to produce better segmentations than the features based on wavelet coefficients and Haralick features for classifiers of low complexity.
Keywords :
feature extraction; geophysical image processing; geophysics computing; image classification; image segmentation; image texture; oceanographic techniques; pattern clustering; sand; sediments; sonar imaging; statistical analysis; synthetic aperture sonar; wavelet transforms; Haralick features; autocorrelation features; biorthogonal wavelets; coral; high-resolution synthetic aperture sonar; intensity image; low complexity classifiers; mud; parameterized SAS image texture model; ripple texture; rock texture; sand ripple; sea grass; seabed environment; seabed texture labeling; seabed texture segmentation; statistical features; synthetic aperture sonar image seabed segmentation; system; texture class; unsupervised multiclass k-means segmentation algorithm; wavelet coefficient; Correlation; Feature extraction; Image segmentation; Mathematical model; Rocks; Synthetic aperture sonar; Vectors; Autocorrelation; expectation-maximization algorithm; image segmentation; synthetic aperture sonar; wavelet coefficients;
Conference_Titel :
Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
978-1-4577-0652-3
DOI :
10.1109/ICSMC.2011.6084185