基于卷积神经网络算法的农业高光谱图像分类比较
Comparison of CNN Algorithms on Hyperspectral Image Classification in Agricultural Lands.
机构信息
Graduate Institute of Communication Engineering, National Taiwan University, Taipei 10617, Taiwan.
出版信息
Sensors (Basel). 2020 Mar 20;20(6):1734. doi: 10.3390/s20061734.
Several versions of convolutional neural network (CNN) were developed to classify hyperspectral images (HSIs) of agricultural lands, including 1D-CNN with pixelwise spectral data, 1D-CNN with selected bands, 1D-CNN with spectral-spatial features and 2D-CNN with principal components. The HSI data of a crop agriculture in Salinas Valley and a mixed vegetation agriculture in Indian Pines were used to compare the performance of these CNN algorithms. The highest overall accuracy on these two cases are 99.8% and 98.1%, respectively, achieved by applying 1D-CNN with augmented input vectors, which contain both spectral and spatial features embedded in the HSI data.
已经开发出了几种卷积神经网络 (CNN) 版本来对农业用地的高光谱图像 (HSI) 进行分类，包括对逐个像素的光谱数据进行分类的 1D-CNN、对选择的波段进行分类的 1D-CNN、对光谱-空间特征进行分类的 1D-CNN 和对主成分进行分类的 2D-CNN。使用萨利纳斯谷的作物农业和印第安松的混合植被农业的 HSI 数据来比较这些 CNN 算法的性能。在这两种情况下，应用包含 HSI 数据中嵌入的光谱和空间特征的扩充输入向量的 1D-CNN 分别实现了 99.8%和 98.1%的最高总体精度。
Zotero 插件