Recognition of roads and bridges in SAR images

摘要

A model-based method is presented for recognition of roads and bridges in fully polarimetric Synthetic Aperture Radar (SAR) images. Polarimetric SAR features and geometric attributes of roads and bridges are used for segmentation, morphological filtering and recognition of roads and bridges. Roads and bridges are often segmented into small disconnected regions due to the presence of interfering objects. A series of Hough transformations are used to group the small regions, for recognition of bridges, a Constant False Alarm Rate (CFAR) detector is first used to extract strong backscatterers from bridge fences, the detected strong backscatterers are next grouped by a Hough transformation to find potential bridge fences, and bridges are then recognized using the polarimetric features of the regions between the potential fences. After recognition of bridges, a different Hough transformation is used to recognize roads. High-resolution SAR images acquired from MIT Lincoln Laboratory are used to illustrate our method.