Fractal Analysis of Seafloor Textures for Target Detection in Synthetic Aperture Sonar Imagery

Abstract

Fractal analysis of an image is a mathematical approach to generate surface related features from an image or image tile that can be applied to image segmentation and to object recognition. In undersea target countermeasures, the targets of interest can appear as anomalies in a variety of contexts, visually different textures on the seafloor. In this thesis, we evaluate the use of fractal dimension as a primary feature and related characteristics as secondary features to be extracted from synthetic aperture sonar (SAS) imagery for the purpose of target detection. We develop three separate methods for computing fractal dimension and produce both primary “slope” and secondary “intercept” and “lacunarity” features as candidates for classification application. Tiles with targets are compared to others from the same background textures without targets. The different features produced are tested with respect to how well they can be used to detect targets vs. false alarms within the same contexts. These features are evaluated for utility using sets of image tiles extracted from a SAS data set generated by the U.S. Navy in conjunction with the Office of Naval Research. We find that almost all features produced have potential to perform well in real-world classification tasks, with the slope and intercept features from a fractional Brownian motion model performing the best among those from the three individual methods. We also find that the secondary intercept features are just as useful, if not more so, in classifying false alarms vs. targets when compared to the primary slope features. The secondary lacunarity features, however, dominate as the most useful features produced. We also do experiments to address the high amount of compute time required to produce the features and to discover how the features change with distance from the image sensor.