Translator Disclaimer
21 September 2004 Improved processing-string fusion-approach investigation for automated sea-mine classification in shallow water
Author Affiliations +
An improved sea mine computer-aided-detection/computer-aided-classification (CAD/CAC) processing string has been developed. This robust automated processing string involves the fusion of the outputs of unique mine classification algorithms. The overall CAD/CAC processing string consists of pre-processing, adaptive clutter filtering (ACF), normalization, detection, feature extraction, optimal subset feature selection, feature orthogonalization, classification and fusion processing blocks. The range-dimension ACF is matched both to average highlight and shadow information, while also adaptively suppressing background clutter. For each detected object, features are extracted and processed through an orthogonalization transformation, enabling an efficient application of the optimal log-likelihood-ratio-test (LLRT) classification rule, in the orthogonal feature space domain. The classified objects of 4 distinct processing strings are fused using the classification confidence values as features and “M-out-of-N”, or LLRT-based fusion rules. The utility of the overall processing strings and their fusion was demonstrated with new shallow water high-resolution sonar imagery data. The processing string detection and classification parameters were tuned and the string classification performance was optimized, by appropriately selecting a subset of the original feature set. Two significant improvements were made to the CAD/CAC processing string by employing sub-image adaptive clutter filtering (SACF) and utilizing a repeated application of the subset feature selection/feature orthogonalization/LLRT classification blocks. It was shown that LLRT-based fusion of the CAD/CAC processing strings outperforms the “M-out-of-N” algorithms and results in up to a seven-fold false alarm rate reduction, compared to the best single CAD/CAC processing string results, while maintaining a high correct mine classification probability. Alternately, the fusion of the processing strings enabled correct classification of almost all mine targets, while simultaneously maintaining a very low false alarm rate. A novel investigation was also presented that illustrates and provides insights on the increased performance gains provided by utilizing LLRT-based fusion of all the different combinations of 2, 3 or 4 distinct processing strings.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tom Aridgides, Manuel F. Fernandez, and Gerald J. Dobeck "Improved processing-string fusion-approach investigation for automated sea-mine classification in shallow water", Proc. SPIE 5415, Detection and Remediation Technologies for Mines and Minelike Targets IX, (21 September 2004);

Back to Top