Feature Extraction for Early Auditory-Visual Integration

Sonar operators combine auditory and visualinformation to make decisions relating to target detection andidentification. Many past attempts to automate the role of sonaroperators have only considered the visual information and havebeen unsuccessful. An assessment has been made of the auditorycomponent of the sonar operator role. This information has beenused to select three algorithms with the potential for detectingfeatures that discriminate between target types. Results arepresented of the application of these algorithms to relevant timeseries data. Subsequently the usage of these features is discussedin terms of the concept of early auditory-visual integration.