Texture-Sensitive Superpixeling and Adaptive Thresholding for Effective Segmentation of Sea Ice Floes in High-Resolution Optical Images
Texture-Sensitive Superpixeling and Adaptive Thresholding for Effective Segmentation of Sea Ice Floes in High-Resolution Optical Images
复制标题
DOI：
10.1109/jstars.2020.3040614
复制
发表时间：
2021
影响因子：
5.5
通讯作者：
Yanmei Chai;Jinchang Ren;B. Hwang;Jian Wang;Dan Fan;Yijun Yan;Shiwei Zhu
中科院分区：
文献类型：
--
作者：
Yanmei Chai;Jinchang Ren;B. Hwang;Jian Wang;Dan Fan;Yijun Yan;Shiwei Zhu
从高分辨率光学（HRO）遥感图像中高效、准确地分割海冰是理解海冰演变和气候变化的关键，特别是在处理大数据量时。现有方法存在噪声干扰和冰水混合的问题，分割误差大，鲁棒性差。在这篇文章中，我们提出了一种新的海冰浮冰分割算法从HRO图像的纹理敏感的超像素化和两阶段阈值的基础上。首先利用鲁棒主成分分析（RPCA）从HRO图像中提取稀疏成分，并通过双边滤波器去除噪声。通过将低秩矩阵和稀疏分量相结合来获得增强图像。其次，纹理敏感的简单线性迭代聚类（SLIC）超像素算法的增强HRO图像的预分割。第三，基于学习的自适应阈值在两个阶段中被用来从导出的超像素块生成精细分割。所提出的方法的有效性进行了验证，两个HRO图像使用视觉评估，定量评价（7个指标），直方图比较。所提出的方法的上级性能证明了其有效性的海冰浮冰分割。
Efficient and accurate segmentation of sea ice floes from high-resolution optical (HRO) remote sensing images is crucial for understanding of sea ice evolutions and climate changes, especially in coping with the large data volume. Existing methods suffer from noise interference and the mixture of water and ice caused high segmentation error and less robustness. In this article, we propose a novel sea ice floe segmentation algorithm from HRO images based on texture-sensitive superpixeling and two-stage thresholding. First, sparse components are extracted from the HRO images using the robust principal component analysis (RPCA), and noise is removed by the bilateral filter. The enhanced image is obtained by combining the low-rank matrix and the sparse components. Second, a texture-sensitive simple linear iterative clustering (SLIC) superpixel algorithm is introduced for presegmentation of the enhanced HRO image. Third, a learning-based adaptive thresholding in the two stages is employed to generate the refined segmentation from the derived superpixels blocks. The efficacy of the proposed method is validated on two HRO images using visual assessment, quantitative evaluation (with seven metrics), and histogram comparison. The superior performance of the proposed method has demonstrated its efficacy for sea ice floe segmentation.