Evaluating the benefits of assisted target recognition

Image exploitation systems that employ automatic target recognition (ATR) technology generally require that a human-in-the-loop validates the ATR results, i.e. assisted target recognition. To evaluate the benefits of assisted target recognition, one must first understand the human's interaction...

Full description

Saved in:
Bibliographic Details
Published inProceedings 30th Applied Imagery Pattern Recognition Workshop (AIPR 2001). Analysis and Understanding of Time Varying Imagery pp. 39 - 45
Main Authors Eckstein, B.A., Irvine, J.M.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2001
Subjects
Algorithm design and analysis
Automation
Electronic mail
Humans
Image analysis
Monitoring
Performance analysis
Software architecture
Software testing
Target recognition
Online AccessGet full text

Cover

More Information
Summary:Image exploitation systems that employ automatic target recognition (ATR) technology generally require that a human-in-the-loop validates the ATR results, i.e. assisted target recognition. To evaluate the benefits of assisted target recognition, one must first understand the human's interaction with the ATR algorithms plus the many factors that influence the performance of both the imagery analyst and the ATR. Thus, any assessment of assisted target recognition must be designed so that performance differences due to ATR assistance are isolated from other factors that affect image exploitation. An aided target acquisition perception testing (ATAPT) demonstration created procedures for assessing assisted and unassisted image exploitation, validating the methodology, metrics and software architecture. This paper describes the ATAPT demonstration and discusses the insights gained from this exercise that will improve future evaluations of systems that use ATR-assisted image exploitation.
ISBN:0769512453
9780769512457
DOI:10.1109/AIPR.2001.991201