Sea ice observations through satellite imaging have led to advancements in environmental research, ship navigation, and ice hazard forecasting in cold regions. Machine learning and, recently, deep learning techniques are being explored by various researchers to process vast amounts of Synthetic Aperture Radar (SAR) data for detecting potential hazards in navigational routes. Detection of hazards such as sea ice floes in Marginal Ice Zones (MIZs) is quite challenging as the floes are often embedded in a multiscale ice cover composed of ice filaments and eddies in addition to floes. This study proposes a segmentation model tailored for detecting ice floes in SAR images. The model exploits the advantages of both convolutional neural networks and convolutional conditional random field (Conv-CRF) in a combined manner. The residual UNET (RES-UNET) computes expressive features to generate coarse segmentation maps while the Conv-CRF exploits the spatial co-occurrence pairwise potentials along with the RES-UNET unary/segmentation maps to generate final predictions. The whole pipeline is trained end-to-end using a dual loss function. This dual loss function is composed of a weighted average of binary cross entropy and soft dice loss. The comparison of experimental results with the conventional segmentation networks such as UNET, DeepLabV3, and FCN-8 demonstrates the effectiveness of the proposed architecture.

No abstract

River ice segmentation, used for surface ice concentration estimation, is important for validating river processes and ice-formation models, predicting ice jam and flooding risks, and managing water supply and hydroelectric power generation. Furthermore, discriminating between anchor ice and frazil ice is an important factor in understanding sediment transport and release events. Modern deep learning techniques have proved to deliver promising results; however, they can show poor generalization ability and can be inefficient when hardware and computing power is limited. As river ice images are often collected in remote locations by unmanned aerial vehicles with limited computation power, we explore the performance-latency trade-offs for river ice segmentation. We propose a novel convolution block inspired by both depthwise separable convolutions and local binary convolutions giving additional efficiency and parameter savings. Our novel convolution block is used in a shallow architecture which has 99.9% fewer trainable parameters, 99% fewer multiply–add operations, and 69.8% less memory usage than a UNet, while achieving virtually the same segmentation performance. We find that the this network trains fast and is able to achieve high segmentation performance early in training due to an emphasis on both pixel intensity and texture. When compared to very efficient segmentation networks such as LR-ASPP with a MobileNetV3 backbone, we achieve good performance (mIoU of 64) 91% faster during training on a CPU and an overall mIoU that is 7.7% higher. We also find that our network is able to generalize better to new domains such as snowy environments.