基于Multiloss-SAM-ConvLSTM的北极航道独立海冰运动预测
DOI:
作者:
作者单位:

1.中国科学院大学;2.中国科学院上海技术物理研究所 中国科学院红外探测与成像技术重点实验室

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(31970378),江苏省水利科技项目(2020068),上海市市级科技重大专项(2017SHZDZX01)


Prediction of independent sea ice motion in Arctic channel based on Multiloss-SAM-ConvLSTM
Author:
Affiliation:

1.University of Chinese Academy of Sciences;2.Key Laboratory of Infrared System Detection and Imaging Technology,Shanghai Institute of Technical Physics Chinese Academic of Sciences

Fund Project:

Supported by National Natural Science Foundation of China (31970378), the Water Conservancy Science and Technology Project of Jiangsu Province (2020068), and Shanghai Municipal Science and Technology Major Project (2017SHZDZX01)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    北极航道海冰运动的准确预测对于保证航行安全、评估航道可通行性和动态修正航线具有重要的指导意义。传统的光流法无法满足海冰运动预测任务中“时空预测+语义分割”的要求。为此,基于MERSI-Ⅱ影像制作了海冰运动数据集SeaiceMoving,提出了一种基于Multiloss-SAM-ConvLSTM的海冰运动预测算法,该算法在SAM-ConvLSTM的基础上引入加权的FDWloss,强化了各节点空间语义的获取。针对样本分布不平衡,讨论了后端分割阈值的偏移效应,通过网格搜索确定最佳分割阈值,提高了海冰整体预测结果。实验结果表明,该方法的Kappa系数为0.75,IOU为0.61,Dice系数为0.76,相较于SAM-ConvLSTM,分别提高了0.1,0.12和0.1,对运动后海冰的位置预测和形状提取能力均有提升,减少了海冰“粘连”的情况。此外,该算法对薄云干扰下的海冰运动依然具备良好的预测能力,可以为北极航线的动态规划和航线修正提供较为准确的技术支撑。

    Abstract:

    Accurate prediction of independent sea ice motion in arctic shipping lanes is of great guiding significance for ensuring navigation safety, assessing navigation navigability and dynamically correcting shipping lanes. However, the traditional optical flow method can not meet the requirement of "spatio-temporal prediction + semantic segmentation". In this paper, the sea ice motion data set SeaiceMoving was made based on MERSI-Ⅱ image and a sea ice motion prediction algorithm based on Multiloss-SAM-ConvLSTM was proposed, introducing weighted FDWloss based on SAM-ConvLSTM to enhance the acquisition of spatial semantics of each node. Aiming at the imbalanced sample distribution, we discussed the offset effect of back-end segmentation threshold. The optimal segmentation threshold is determined by grid search method, which improves the overall prediction result of sea ice motion. The experimental results indicate that the Kappa coefficient, IOU coefficient and Dice coefficient of the proposed method are 0.75, 0.61 and 0.76 respectively. Compared with SAM-ConvLSTM, they are improved by 0.1, 0.12 and 0.1 respectively. Furthermore, the proposed method can improve the position prediction and shape recovery ability of sea ice after motion and reduce the "adhesion" of sea ice. In addition, the algorithm can still effectively predict the sea ice motion under the interference of thin clouds, which can provide more accurate technical support for the dynamic planning and route correction of the Arctic route.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-01-28
  • 最后修改日期:2022-04-13
  • 录用日期:2022-04-14
  • 在线发布日期:
  • 出版日期: