Fusion of Spaceborne and Airborne SAR Images via Target Proposal and Polarization Information Exploitation for Vessel Detection

In this paper, we focus on the vessel detection via fusion of synthetic aperture radar (SAR) images acquired from spaceborne-airborne collaborative observations, and propose a new method based on target proposal and polarization information exploitation (TPPIE). First, a new triple-state proposal matrix (TSPM) is generated by combing the normed gradient-based target proposal and the edge-based morphological candidate map. Second, we present a new polarization feature, named absolute polarization ratio (APR), to exploit the intensity information of dual-polarization SAR images. Third, the final fused image with enhanced targets and suppressed backgrounds, i.e., improved target-to-cluster ratio (TCR), is attained by the Hadamard product of the intersected TSPM from multi-sources and the composite map exploiting APR feature. Experimental results using Gaofen-3 satellite and unmanned aerial vehicle (UAV) SAR images show that the proposed TPPIE fusion method yields higher TCRs of fused images and better detection performance of vessel targets than the commonly used image fusion approaches.