基于残差网络特征融合的高光谱图像分类

韩彦岭, 崔鹏霞, 杨树瑚, 刘业锟, 王静, 张云

Classification of hyperspectral image based on feature fusion of residual network

HAN Yanling, CUI Pengxia, YANG Shuhu, LIU Yekun, WANG Jing, ZHANG Yun

表7 不同卷积核个数下巢湖数据的分类结果

Tab.7 Classification results of Chaohu Lake data with different numbers of convolution kernels

结果 8 16 32 40 OA/% 87.00±1.09 90.20±1.54 91.31±3.07 89.48±4.18 Kappa×100 80.78±1.49 85.49±0.74 87.14±4.64 84.45±7.38