A Method to Mitigate the Influence of Rain on Wind Direction Estimation From X-band Marine Radar Images

In this paper, a novel scheme is employed to mitigate the influence of rain on wind direction estimation from X-band marine radar data. Rain-contaminated regions with blurry wave signatures are first identified using the self-organizing-map (SOM)-based clustering model. Pixels located in those regions are then corrected using a deep-neural-network-based image dehazing model called DehazeNet. After obtaining the rain-corrected radar image, wind direction can be obtained using the classic curve-fitting-based method. Shipborne marine radar data collected under precipitation in a sea trial off the east coast of Canada are utilized to validate the proposed scheme. Experimental results show that the accuracy of wind direction estimation is significantly improved using the proposed scheme with a reduction of root mean square deviation (RMSD) by 19.1 degrees.