Fuzzy rule based fusion technique to automatically detect aircraft in SAR images

Fuzzy reasoning through fuzzy rule combination is used to improve the accuracy of the automatic detection of aircraft in synthetic aperture radar (SAR) images using a priori knowledge derived from colour aerial photographs. A combination of the fuzzy automatic target recognition system with neural networks is used to fuse object identity attribute data derived from a SAR and a colour aerial photo image. The images taken by the two different sensors have quite different resolutions and are taken at different times. The aim of the study is to automatically detect ground based aircraft in the SAR image with greater certainty. Using the fusion techniques the authors have correctly detected five of the six aircraft (83% accuracy rate) and reduced the number of false alarms from forty to eight when compared to the output of the background discrimination algorithm.