Selecting discriminate features and constructing an appropriate classifier are two essential factors for ship classification in a synthetic aperture radar (SAR) image. Unfortunately, these two factors are rarely considered together by existing studies. We propose a joint feature and classifier selection method by integrating the classifier selection strategy into a wrapper feature selection framework. The sequential forward floating searching algorithm is improved to conduct efficient searching for an optimal triplet of feature-scaling-classifier. Comprehensive experiments on two data sets demonstrate that the proposed method can select the optimal combination of a nonredundant complementary feature subset, appropriate scaling, and classifier to improve the performance of ship classification in a SAR image.

This letter presents a novel method for ship classification that uses synthetic-aperture-radar images to distinguish ships based on superstructure scattering features. The ratio of dimensions, which combines the 2-D and 3-D properties of scattering, is explored as an effective and credible means to describe the scattering features of ships. The proposed method consists of three main stages: 1) ship isolation from the sea; 2) parametric vector (F) estimation; and 3) categorization using a support vector machine (SVM) classifier. To depict ship features more accurately and reduce feature redundancy, we propose employing peak extraction to divide a ship into bow, middle, and stern instead of into three equal parts. The classification method is tested with RadarSat-2 images, and ground-truth information is supplied by an automatic identification system. The experimental results show that the proposed method can achieve satisfactory ship-classification performance compared with existing methods, with an overall accuracy exceeding 80%.

Sea ice type is one of the most sensitive variables in Arctic ice monitoring and detailed information about it is essential for ice situation evaluation, vessel navigation, and climate prediction. Many machine-learning methods including deep learning can be employed for ice-type detection, and most classifiers tend to prefer different feature combinations. In order to find the optimal classifier-feature assembly (OCF) for sea ice classification, it is necessary to assess their performance differences. The objective of this letter is to make a recommendation for the OCF for sea ice classification using Cryosat-2 (CS-2) data. Six classifiers including convolutional neural network (CNN), Bayesian, K nearest-neighbor (KNN), support vector machine (SVM), random forest (RF), and back propagation neural network (BPNN) were studied. CS-2 altimeter data of November 2015 and May 2016 in the whole Arctic were used. The overall accuracy was estimated using multivalidation to evaluate the performances of individual classifiers with different feature combinations. Overall, RF achieved a mean accuracy of 89.15%, followed by Bayesian, SVM, and BPNN (~86%), outperforming the worst (CNN and KNN) by 7%. Trailing-edge width (TeW) and leading-edge width (LeW) were the most important features, and feature combination of TeW, LeW, Sigma0, maximum of the returned power waveform (MAX), and pulse peakiness (PP) was the best choice. RF with feature combination of TeW, LeW, Sigma0, MAX, and PP was finally selected as the OCF for sea ice classification and the results that demonstrated this method achieved a mean accuracy of 91.45%, which outperformed the other state-of-art methods by 9%.

This study uses the Argos satellite‐tracked surface drifter trajectory data and ENVISAT (European satellite) ASAR (advanced synthetic aperture radar) images to illustrate the ocean vortex trains (OVT) in the Luzon Strait. Two cases that occurred in the northwest of Babuyan Island are observed. The first train of three cyclonic vortices showed up on drifter trajectories from 20° to 20.5°N and from 120° to 121°E, and the second, consisting of five pairs of cyclonic‐anticyclonic vortices, occurred on the upstream side of the first one from 19.5° to 20.0°N and from 121.0° to 122.0°E and showed up on the ASAR images acquired on 19 November 2006. The total length of the vortex train axis reaches about 250 km. All vortices propagate northwestward (∼315° TN). The mean angular velocity is (2.07 ± 0.18) × 10⁻⁵ s⁻¹. Theoretical models of ocean vortex radar image derived from radar imaging theories are used to extract dynamical parameters from ASAR imagery signatures, which include the distance between two consecutive vortices and that between two rows of vortices of (22.6 ± 1.9) km and (8.2 ± 1.2) km, respectively, the maximum rotational velocity radius as 4.70 km, and the vortex rotational angular velocity 3 × 10⁻⁵s⁻¹. Dynamical analyses give the mean velocity of the current of 0.65 ms⁻¹, and the propagation velocity of the vortex 0.58 ms⁻¹. The vortex shedding rate is estimated as 2.57 × 10⁻⁵ s⁻¹. The Reynolds number is estimated as 50 to 500. For the individual vortex and the vortex train, the Rossby numbers are O(0.4), and O(0.5), respectively, implying that both vortex and vortex train observed in the Luzon Strait have a sub‐mesoscale nature. This study also reveals a strong current with an average surface current velocity of around 0.7 ms⁻¹ and the direction of around 315° TN flowing directly from the Pacific to SCS passing through the southern Luzon Strait. The mean flow velocity can be calculated using methods developed in this study and OVT dynamical models. This information may provide more insight to the circulation systems in the area including the origin of Kuroshio.