Feature extraction for early auditory-visual integration

Sonar operators combine auditory and visual information to make decisions relating to target detection and identification. Many past attempts to automate the role of sonar operators have only considered the visual information and have been unsuccessful. An assessment has been made of the auditory component of the sonar operator role. This information has been used to select three algorithms with the potential for detecting features that discriminate between target types. Results are presented of the application of these algorithms to relevant time series data. Subsequently the usage of these features is discussed in terms of the concept of early auditory-visual integration.