Reconstruction and fusion of perceptual features for automatic classification of sonar echoes

The long detection ranges provided by low-frequency active sources present many advantages to localize and track underwater threats from safe distances. However, in littoral environments, echoes from naturally occurring features cause false alarms which degrade the overall system performance. The use of perceptual features derived from those used in the human auditory system (aural features), has been shown to allow discrimination between target and clutter echoes for both impulsive [1] and coherent [2] sources. The present work extends these findings by examining the effect of the sonar bandwidth on these kinds of features using a large data set gathered during an experiment on the Malta Plateau. Two separate bandwidths corresponding to those of two acoustic sources used during the experiment are considered independently. Using echoes from the two sources considered separately, it is possible to effectively reconstruct many of the features that would be derived with a full bandwidth signal. The results have implications for the use of fusion techniques where two separate sources are employed cooperatively and fused at the feature level to classify targets. Next, by using only those features that can effectively be reconstructed, it is possible to examine the full effect of bandwidth on the performance of a classification system which uses aural features. Results show that the system performance can be maintained with a narrower bandwidth if the center frequency is shifted downwards. Finally, fusion of the two sources at the decision-level is presented. Using the technique described, it is possible to achieve the same performance as a system using a single broadband source.