| Abstract | Rapid ice recession in the Arctic Ocean, with predictions of ice-free summers by 2060, opens new maritime routes but requires reliable navigation solutions. Current approaches rely heavily on subjective expert judgment, underscoring the need for automated, data-driven solutions. This study leverages machine learning to assess ice conditions using ship-borne optical data, and introduces a semi-manual, region-based annotation technique to alleviate the high cost of manual annotation for close-range shipborne ice data. The resulting dataset was used to train and evaluate the proposed video segmentation model, UPerFlow, which advances the SegFlow architecture by incorporating a six-channel ResNet encoder, separate UPerNet-based segmentation decoders for each image, PWCNet as the optical flow encoder, and cross-connections that integrate bi-directional flow features without loss of latent information. The proposed architecture outperforms baseline image segmentation networks by an average 38 % in occluded regions, demonstrating the robustness of video segmentation in addressing challenging Arctic conditions. |
|---|
