User guided visualization for target search

Abstract

Automated target cueing (ATC) can assist analysts in searching large volumes of imagery. Performance of most automated systems is less than perfect, requiring an analyst to review the results to dismiss false alarms or confirm correct detections. This paper explores methods for improving the presentation and visualization of the ATC output, enabling more efficient and effective review of the detections flagged by the ATC. The approach relies on the interaction between the user and the ATC results. Confirmation of correct detections and dismissal of false alarms provides information to update the visualization. We present a description of the visualization method and illustrate it with results using panchromatic imagery of vehicles.