In this paper, a temporal convolutional network (TCN)-based model is proposed to retrieve significant wave height (Hs) from X-band nautical radar images. Three types of features are first extracted image sequences based on signal noise ratio (SNR), ensemble empirical mode decomposition (EEMD), and gray level co-occurrence matrix (GLCM) methods, respectively. Then, feature vectors input into the TCN-based regression produce Hs estimation. Radar data collected moving vessel at East Coast...

In this article, the accuracy of wave direction and period estimation from <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">X</i> -band marine radar images under different rain rates is analyzed, a simple subimage selection scheme proposed to mitigate effect. First, each image divided into multiple subimages, subimages with relatively clear signatures are identified based on random-forest-based classification model. Then, estimated by...

The presence of rain can negatively affect the performance many sensors such as X-band radar. In this paper, an effective approach is proposed to mitigate effect on significant wave height ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${H}_{s}$ </tex-math></inline-formula> ) estimation from radar sensor data along with a machine-learning (ML)-based method. First all, haze removal algorithm applied...

This paper presented a novel significant wave height (SWH) estimation method, SWHFormer, which incorporates the Vision Transformer (ViT) to estimate SWH from X-band nautical radar images. Unlike traditional convolutional neural networks, ViT model treats input as sequence, capitalizing on its attention mechanism capture long-range dependencies, resulting in superior performance capturing complex patterns present sea dynamics. The data undergo an image denoising routine, followed by patching,...

In the paper, a variational mode decomposition (VMD)-based method is proposed to estimate significant wave heights (<i>H_s</i>) from X-band marine radar images. Firstly, 10 intrinsic functions (IMFs) are decomposed selected sub-images with VMD. Then, linear fitting conducted <i>H_s</i> by using sum of amplitude modulation (AM) components extracted 6^<i>th</i> 9^<i>th</i> IMFs. The data were collected ship at sea around 300 km Halifax, NS, Canada....

As a result of the rain contamination on radar images, accuracy significant wave height (SWH) estimation from images collected under rainy conditions is adversely affected. This paper presents novel approach for enhancing SWH rain-contaminated by combining DehazeNet and convolutional gated recurrent unit (CGRU) networks. Firstly, CNN-based dehazing algorithm, i.e., DehazeNet, employed to correct visual degradation caused in images. Subsequently, CGRU network utilized perform further...

This paper presents an improved algorithm for retrieving ocean surface currents from X-band marine radar images. The original polar current shell (PCS) method begins with a 3D fast Fourier transform (FFT) of the image sequence, followed by extraction dispersion spectrum, which is then transformed into PCS using coordinates. Building on this foundation, approach to analyze all data points corresponding different wavenumber magnitudes in domain rather than analyzing each specific magnitude...

Due to the sensitivity of X-band signal rain, rain may affect precision oceanic parameters retrieval from marine radar images. In this paper, a vision transformer (ViT)-based approach is proposed detect in data, allowing recognition rain-contaminated Given its ability capture long-range dependencies images and model global context effectively, ViT considered as promising alternative convolutional neural networks (CNNs) for image classification tasks. Each first preprocessed then separated...

A state-of-the-art machine learning based significant wave height (H <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">s</inf> ) estimation model, which is on a temporal convolutional network (TCN), proposed for X-band marine radar in this paper. The input space of the composed three features (i.e., signal-to-noise ratio (SNR)-based, ensemble empirical mode decomposition (EEMD)-based, and gray level co-occurrence matrix features) extracted from...

In this work, an improvement for the quality of X-band radar images affected by rain is proposed, and a support vector regression (SVR)-based method designed to further obtain significant wave height (H <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">s</inf> ). The first step implement dehazing algorithm on influenced rain. Then, SVR employed train H model including two features, i.e., gray level co-occurrence matrix (GLCM) signal-to-noise ratio...

In this paper, the accuracy of wave direction estimation from X-band marine radar images under different rain rates is analyzed, and a simple sub-image selection scheme proposed to mitigate effect. First, each image divided into multiple sub-images, sub-images with relatively clear signatures are identified based on random-forest-based classification model. Then, estimated by performing Radon transform valid sub-image. The shore-based images, simultaneous rate data, as well buoy-measured...