Target detection in SAR imagery by genetic programming

摘要: Abstract The automatic detection of ships in low-resolution synthetic aperture radar (SAR) imagery is investigated this article. detector design objectives are to maximise accuracy across multiple images, minimise the computational effort during image processing, and stage. results an extensive numerical study show that a novel approach, using genetic programming (GP), successfully evolves detectors which satisfy earlier objectives. Each represents algebraic formula thus principles can be discovered reused. This major advantage over artificial intelligence techniques use more complicated representations, e.g. neural networks.