Simulated target insertion for automatic target recognition performance estimation

Abstract

To support automatic target recognition (ATR) algorithm development as well as predict their performance in various operational environments, there is a need for more realistic sonar data that captures environmental effects that are not only difficult to model using physical acoustical models but expensive to measure in the real world. Previous target insertion efforts have focused on high frequency imaging sonar. As such, these efforts effectively combine only the magnitudes of the real and simulated data. This effort will focus on low frequency sonar, and the goal is to retain the phase by combining the complex data where possible. Maintaining the phase allows us to take advantage of the resonant frequency information available in the lower frequency bands, which is lost when the magnitudes are summed. In this effort, several approaches to inserting simulated target data into real sonar data will be investigated. Typically, there are no shadows in the low frequency images; therefore, none of the approaches investigated here take shadows into account. For each method, an analysis will be carried out to evaluate how the simulated targets behave compared to real targets. These analyses will be performed on real and simulated image snippets, gradients of snippets, and the frequency content of the target scattering response or acoustic color plots. The analysis will include several statistical measures which will be used to compare snippets of real and simulated targets as well as backgrounds of their immediate surroundings.To support automatic target recognition (ATR) algorithm development as well as predict their performance in various operational environments, there is a need for more realistic sonar data that captures environmental effects that are not only difficult to model using physical acoustical models but expensive to measure in the real world. Previous target insertion efforts have focused on high frequency imaging sonar. As such, these efforts effectively combine only the magnitudes of the real and simulated data. This effort will focus on low frequency sonar, and the goal is to retain the phase by combining the complex data where possible. Maintaining the phase allows us to take advantage of the resonant frequency information available in the lower frequency bands, which is lost when the magnitudes are summed. In this effort, several approaches to inserting simulated target data into real sonar data will be investigated. Typically, there are no shadows in the low frequency images; therefore, none of the approac...