Bankline detection of GF-3 SAR images based on shearlet

The GF-3 satellite is China’s first self-developed active imaging C-band multipolarization synthetic aperture radar (SAR) satellite with complete intellectualproperty rights, which is widely used in various fields. Among them, the detectionand recognition of banklines of GF-3 SAR image has very important applicationvalue for map matching, ship navigation, water environment monitoring and otherfields. However, due to the coherent imaging mechanism, the GF-3 SAR imagehas obvious speckle, which affects the interpretation of the image seriously. Based onthe excellent multi-scale, directionality and the optimal sparsity of the shearlet, abankline detection algorithm based on shearlet is proposed. Firstly, we use non-localmeans filter to preprocess GF-3 SAR image, so as to reduce the interference ofspeckle on bankline detection. Secondly, shearlet is used to detect the bankline of theimage. Finally, morphological processing is used to refine the bankline and furthereliminate the false bankline caused by the speckle, so as to obtain the idealbankline detection results.