River ice monitoring is of great significance for river management, ship navigation and ice hazard forecasting in cold-regions. Accurate ice segmentation is one most important pieces of technology in ice monitoring research. It can provide the prerequisite information for the calculation of ice cover density, drift ice speed, ice cover distribution, change detection and so on. Unmanned aerial vehicle (UAV) aerial photography has the advantages of higher spatial and temporal resolution. As UAV technology has become more popular and cheaper, it has been widely used in ice monitoring. So, we focused on river ice segmentation based on UAV remote sensing images. In this study, the NWPU_YRCC dataset was built for river ice segmentation, in which all images were captured by different UAVs in the region of the Yellow River, the most difficult river to manage in the world. To the best of our knowledge, this is the first public UAV image dataset for river ice segmentation. Meanwhile, a semantic segmentation deep convolution neural network by fusing positional and channel-wise attentive features is proposed for river ice semantic segmentation, named ICENET. Experiments demonstrated that the proposed ICENET outperforms the state-of-the-art methods, achieving a superior result on the NWPU_YRCC dataset.

Accurate ice segmentation is one of the most crucial techniques for intelligent ice monitoring. Compared with ice segmentation, it can provide more information for ice situation analysis, change trend prediction, and so on. Therefore, the study of ice segmentation has important practical significance. In this study, we focused on fine-grained river ice segmentation using unmanned aerial vehicle (UAV) images. This has the following difficulties: (1) The scale of river ice varies greatly in different images and even in the same image; (2) the same kind of river ice differs greatly in color, shape, texture, size, and so on; and (3) the appearances of different kinds of river ice sometimes appear similar due to the complex formation and change procedure. Therefore, to perform this study, the NWPU_YRCC2 dataset was built, in which all UAV images were collected in the Ningxia–Inner Mongolia reach of the Yellow River. Then, a novel semantic segmentation method based on deep convolution neural network, named ICENETv2, is proposed. To achieve multiscale accurate prediction, we design a multilevel features fusion framework, in which multi-scale high-level semantic features and lower-level finer features are effectively fused. Additionally, a dual attention module is adopted to highlight distinguishable characteristics, and a learnable up-sampling strategy is further used to improve the segmentation accuracy of the details. Experiments show that ICENETv2 achieves the state-of-the-art on the NWPU_YRCC2 dataset. Finally, our ICENETv2 is also applied to solve a realistic problem, calculating drift ice cover density, which is one of the most important factors to predict the freeze-up data of the river. The results demonstrate that the performance of ICENETv2 meets the actual application demand.