Title :
Fusion of intelligent agents for the detection of aircraft in SAR images
Author :
Filippidis, Arthur ; Jain, L.C. ; Martin, N.
Author_Institution :
Land Oper. Div., Defence Sci. & Technol. Organ., Salisbury, SA, Australia
fDate :
4/1/2000 12:00:00 AM
Abstract :
Receiver operating curves are used in the analysis of 20 images using a novel automatic target recognition (ATR) fusion system. Fuzzy reasoning is used to improve the accuracy of the automatic detection of aircraft in synthetic aperture radar (SAR) images using a priori knowledge derived from color aerial photographs. The images taken by the two different sensors are taken at different times. In summarizing the results of our experiments using real and generated targets with noise for a probability of detection of 91.5 percent using the ATR fusion technique, we have improved our false alarm rates by approximately 17 percent over using texture classification
Keywords :
aircraft; fuzzy logic; image recognition; multi-agent systems; object detection; radar imaging; sensor fusion; synthetic aperture radar; ATR fusion system; SAR images; aircraft detection; automatic target recognition; color aerial photographs; fuzzy reasoning; intelligent agent fusion; noise; receiver operating curves; synthetic aperture radar; texture classification; Aircraft; Colored noise; Fusion power generation; Fuzzy reasoning; Image analysis; Image sensors; Intelligent agent; Radar detection; Synthetic aperture radar; Target recognition;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
