Small Fishing Vessel Detection Using Polarimetric Observables Fusion with Dual-Polarization Sentinel-1 SAR Data

Abstract

Synthetic Aperture Radar (SAR) is an efficient tool for monitoring ships. However, the detection accuracy of small fishing vessels is insufficient due to radar characteristics and image quality. Therefore, this study proposes a polarimetric fusion method focused on enhancing the detection performance of small fishing vessels using Sentinel-1 Single Look Complex (SLC) images. A combination of VH and VV polarization channels (fusVH) was applied to minimize radio frequency interference and azimuth smearing in SAR for detecting merchant ships, and the reflection symmetry (sym) was generated exploiting the fusVH image. Afterward, when the difference between sym and fusVH was less than 7.2 (dB) and sym was greater than -18.03 (dB), the maximum values of sym and fusVH were used to enhance the pixels of potential small ships. Using both sym and fusVH, small fishing vessels can be separated from merchant ships, which can be easily detected using fusVH images. The results were validated using 14 scenes from 2021 to 2023, and the average matching results were calculated to be 0.84 for the probability of detection rate and 0.29 for the false alarm rate.