Sea Ice–Water Classification of RADARSAT-2 Imagery Based on Residual Neural Networks (ResNet) with Regional Pooling

Abstract

Sea ice mapping plays an integral role in ship navigation and meteorological modeling in the polar regions. Numerous published studies in sea ice classification using synthetic aperture radar (SAR) have reported high classification rates. However, many of these focus on numerical results based on sample points and ignore the quality of the inferred sea ice maps. We have designed and implemented a novel SAR sea ice classification algorithm where the spatial context, obtained by the unsupervised IRGS segmentation algorithm, is integrated with texture features extracted by a residual neural network (ResNet) and, using regional pooling, classifies ice and water. This algorithm is trained and tested on a published dataset and cross-validated using leave-one-out (LOO) strategy, obtaining an overall accuracy of 99.67% and outperforming several existing algorithms. In addition, visual results show that this new method produces sea ice maps with natural ice–water boundaries and fewer ice and water errors.

Sea Ice Extraction via Remote Sensing Imagery: Algorithms, Datasets, Applications and Challenges

“…Hoekstra et al [40] integrated IRGS segmentation with supervised labeling using RF. The IRGS segmentation algorithm incorporated spatial context and texture features from the ResNet, utilizing region pooling for ice-water classification [41]. Jiang et al [42] made a comparison between two benchmark pixel classifiers, SVM and RF, and two models, IRGS-SVM and IRGS-RF.…”

Ice Identification with Error-Accumulation Enhanced Neural Dynamics in Optical Remote Sensing Images

“…This subsection focuses on the identification of the Arctic sea ice with the aid of EAEND model (10), MNI model (27), NRI model ( 28), and ETZNN model (29) in the noisefree ψ(t) = 0 and the random noise ψ(t) ∈ 5 × [−1, 1] environments, respectively. Notably, some of the initial ice in the Arctic sea ice are not formed and therefore are not included in the experiments.…”

“…This observation aligns with the numerical results and is visually corroborated in Figure 6g. Both MNI model (27) and NRI model ( 28) exhibit a tendency to misclassify fog and fragmented ice as sea ice, yielding Kappa coefficients of 0.455939 and 0.491205, respectively. Additionally, NRI model (28) demonstrates marginally better performance than MNI model (27) in terms of OA, AA, and PP values.…”

“…During the development of machine learning techniques, researchers gradually identify the discrepancy problem between remote sensing image data and ground truth label data. Hence, unsupervised learning methods have emerged, such as generative adversarial networks-based techniques [27,28]. These techniques can categorize remote sensing images of sea ice, even in the absence of labeled data.…”

Research on Remote Sensing Image Segmentation Algorithm Based on Res2Net and SANet

“…The full convolution (FCN) semantic segmentation network is applied to Gaofen-3 remote sensing image to complete the extraction and detection of water, vegetation and buildings by Wang et al [24]. A new SAR sea ice classification algorithm is designed by Jiang et al [25]. The integration of spatial context information, derived from unsupervised segmentation algorithms, with texture features extracted by ResNet, facilitates the classification of ice and water in remote sensing imagery.…”