Abstract
The presence of rain may blur surface wave signatures and cause additional radar backscatter, which negatively affects the performance of ocean remote sensing applications (e.g., ocean surface wind and wave parameter measurement) using X-band marine radars. In this article, a novel end-to-end model is developed to detect and locate rain-contaminated pixels in X-band marine radar images based on a type of deep neural network called SegNet, which is able to segment rain-contaminated regions by classifying each pixel into three classes: rain-free, rain-contaminated, and wind-dominated rain cases. Shipborne marine radar images collected during a sea trial on the East Coast of Canada are first preprocessed and then utilized to train an ensemble of SegNet-based networks. The final classification result of each pixel will be the class chosen by most individual networks. Testing results using images obtained from both shipborne and shore-based marine radar systems manifest that the proposed model effectively segment between rain-free, rain-contaminated, and wind-dominated rain regions, with a pixel classification accuracy of 94.6% and 90.4% for Decca and Koden radar images, respectively.
Highlights
C ONVENTIONAL HH-polarized X-band marine radars scan the sea surface at grazing incidence with high temporal and spatial resolution
Image data collected by two different X-band marine radar systems (i.e., Decca and Koden) at two different locations are used to train the SegNet-based segmentation model and evaluate its performance
Estimation results show that compared to curve fitting directly on original radar images without rain-contaminated region identification, the estimation accuracy is improved with a reduction of 13.2◦ in root mean square difference, which manifests that the proposed method has the potential to further improve the estimation accuracy of other ocean parameters under rain conditions
Summary
C ONVENTIONAL HH-polarized X-band marine radars scan the sea surface at grazing incidence with high temporal and spatial resolution. In the past few years, X-band marine radar images enclosing backscatter intensity information have been applied to various remote sensing purposes and received satisfactory results, such as sea surface wind and wave parameter measurement [2]–[4], surface current determination [5], [6], tide observation [7], and bathymetry estimation [8], [9]. Those methods may not work well under rainy conditions.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
