Automatic ship detection in SAR images

This paper addresses the problem of detecting ships in SAR images in a fully automated way. To obtain high reliability and robustness, the proposed processing chain detects possible targets by first searching in parallel for bright spots, i.e. potential ship bodies, and elongated wakes present in the scene, and then cross-validating the wakes against the bright spots in order to reject false targets. This system produces fuzzy decisions, as it detects bright spots and wakes and then associates with each entity a degree of goodness determined on the basis of suitable fuzzification functions set up during the system training. The whole chain has been implemented and tested on a MicroVax II sequential machine and on a hypercube architecture of IMS T800 transputers