Chen Shengbo, Useya Juliana, Mugiyo Hillary
College of GeoExploration Science and Technology, Jilin University, Changchun, 130026, China.
Department of Geomatics Engineering, University of Zimbabwe, 630 Churchill Avenue, Harare, Zimbabwe.
Heliyon. 2020 Nov 4;6(11):e05358. doi: 10.1016/j.heliyon.2020.e05358. eCollection 2020 Nov.
Radar imagery have few polarization bands which can limit the ability to do traditional digital classification. Harmonization of Sentinel-1 and Landsat 8 data despite having complementary texture information can be a challenge. The objectives of this paper are to explore texture features derived from Landsat 8 OLI and dual-polarized Sentinel-1 SAR speckle filtered and unfiltered backscatter, to aggregate classification results using Decision-Level Fusion (DLF), and to evaluate the performance of decision-level fused maps. Gray Level Co-occurrence Matrix (GLCM) is employed to derive sets of seven texture features for Landsat 8 bands and VV + VH backscatter using 5 × 5, 7 × 7, 9 × 9, and 11 × 11 window sizes. Each texture feature is stacked with a respective source image and classified using Support Vector Machine (SVM). Classified maps from the best three performers from both speckle filtered and unfiltered are aggregated with classified maps from Landsat 8 using plurality voting algorithm and compared using Z-test. Results indicate an overall classification accuracy of 96.02% from DLF images of Landsat and non-speckle filtered maps, whereas Landsat and speckle filtered achieved 94.69%. The best texture information are derived from the blue band followed by the red band, whereas speckle unfiltered textures performed better than speckle filtered textures. We conclude that integration of Landsat 8 and Sentinel-1, either speckle filtered or unfiltered, improves crop classification and speckles do not have statistically significant effects (p = 0.1208).
雷达图像的极化波段较少，这可能会限制进行传统数字分类的能力。尽管哨兵 -1 和陆地卫星 8 数据具有互补的纹理信息，但对它们进行协调仍可能是一项挑战。本文的目的是探索从陆地卫星 8 号操作陆地成像仪（OLI）以及双极化哨兵 -1 合成孔径雷达（SAR）经斑点滤波和未滤波的后向散射中提取的纹理特征，使用决策级融合（DLF）汇总分类结果，并评估决策级融合地图的性能。采用灰度共生矩阵（GLCM），使用 5×5、7×7、9×9 和 11×11 的窗口大小，为陆地卫星 8 号波段以及垂直极化（VV）+水平极化（VH）后向散射提取七组纹理特征。每个纹理特征与相应的源图像堆叠，并使用支持向量机（SVM）进行分类。来自斑点滤波和未滤波的最佳三个分类器的分类地图与陆地卫星 8 号的分类地图使用多数投票算法进行汇总，并使用 Z 检验进行比较。结果表明，陆地卫星和未滤波斑点地图的决策级融合图像的总体分类准确率为 96.02%，而陆地卫星和滤波斑点地图的准确率为 94.69%。最佳纹理信息来自蓝色波段，其次是红色波段，而未滤波斑点纹理的表现优于滤波斑点纹理。我们得出结论，陆地卫星 8 号和哨兵 -1 的整合，无论是滤波还是未滤波的斑点，都能提高作物分类，并且斑点没有统计学上的显著影响（p = 0.1208）。
