Abstract:

With the increasing popularity of using autonomous underwater vehicles (AUVs) to gather large quantities of Synthetic Aperture Sonar (SAS) seafloor imagery, the burden on human operators to identify targets in these seafloor images has increased significantly. Existing methods of automated target detection can have perfect or near-perfect accuracy, but often produce a high ratio of false positives. Thus, it is desired to find features that discriminate between targets and high-confidence false alarms. In this paper, we examine the potential of several classical methods of feature extraction in how well their generated features can separate the two classes of image tiles: those containing targets from those containing no targets. To quantify the ability of a set of features to separate these classes, we measure the region-based cross validation accuracy of a linear SVM trained on the features in question, extracted from SAS imagery provided to us by the U.S. Navy. We show that these general feature extraction methods show potential in the ATR problem, suggesting further research is warranted.

Links:

Citation:

J. Dale, A. Galusha, J. M. Keller and A. Zare, “Evaluation of image features for discriminating targets from false positives in synthetic aperture sonar imagery,” in Proc. SPIE 11012, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIV, 1101205, May 2019. doi: 10.1117/12.2519486

@InProceedings{Dale2019Evaluation_SAS,
Title = {Evaluation of image features for discriminating targets from false positives in synthetic aperture sonar imagery},
Author = {J. Dale and A. Galusha and J. M. Keller and A. Zare},
Booktitle = {Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIV, 110120A},
Series = {Proc. SPIE},
Volume = {11012},
Year = {2019},
Month = {May},
doi = {10.1117/12.2519486},
}