A Novel Algorithm for Bridge Recognition over Water in High Resolution SAR Image

First,2-dimensional feature of gray mean and variance is adopt to the fuzzy segmentation of SAR image. Second,lawn and hill shadow false targets are excluded based on 8-neighbour chain-code tracking edge method. Then the potential edge points of bridge ROIs(regions of interest)obtained by searching the water regions are used to line fitting. In order to avoid the effect of island in river,ships and stripe jamming,the fitted lines are also connected and extended respectively to identify the suspected bridge ROIs. Finally,the suspected bridge ROIs are segmented by double parameter CFAR further,where the false targets are excluded by the principle axis direction and perimeter extracted,and the bridges are recognized and located exactly. Experimental results show the algorithm can recognize the bridges over water accurately in high resolution SAR image,especially the bridges with subtle grey gradient variance or disturbed by stripe jamming.