CFAR Detection of Extended Targets in SAR Images based on goodness-of-fit test

A novel CFAR scheme based on goodness-of-fit (GoF) test is proposed in this paper. This scheme begins with a logarithmic amplifier, which transforms the clutter PDF, whether Weibull or Lognormal into a location-scale one, some relevant properties of which are exploited to ensure CFAR. A Goodness-of-fit test is adopted at last to decide whether the samples from target window belong to the background or are abnormal for it and so should be declared to be a target of interest.