卷积神经网络特征在遥感图像配准中的应用

叶发茂, 罗威, 苏燕飞, 赵旭青, 肖慧, 闵卫东

Application of convolutional neural network feature to remote sensing image registration

Famao YE, Wei LUO, Yanfei SU, Xuqing ZHAO, Hui XIAO, Weidong MIN

表1 不同特征的图像配准精度

Tab.1 Image registration accuracy of different features

特征	P-A图像			P-B图像			P-C图像			P-D图像
特征	$RM S_{all}$	$RM S_{LOO}$	$N_{red}$	$RM S_{all}$	$RM S_{LOO}$	$N_{red}$	$RM S_{all}$	$RM S_{LOO}$	$N_{red}$	$RM S_{all}$	$RM S_{LOO}$	$N_{red}$
SIFT	0.040 8	0.040 9	64	0.092 1	0.094 1	24	0.070 5	0.070 6	42	0.913 4	1.015 0	7
$FC 7_{fine - tuning}$	0.034 2	0.034 2	72	0.079 6	0.081 3	27	0.038 1	0.039 0	49	0.800 2	0.820 2	8
$FC 6_{fine - tuning}$	0.034 2	0.034 2	72	0.079 6	0.081 3	27	0.036 2	0.037 1	50	0.662 2	0.839 8	11
$Agg 1_{fine - tuning}$	0.034 2	0.034 2	72	0.079 6	0.081 3	27	0.036 2	0.037 1	50	0.698 7	1.077 3	10
$Agg 2_{fine - tuning}$	0.034 2	0.034 2	72	0.079 6	0.081 3	27	0.036 2	0.037 1	50	0.670 0	0.714 4	10
$Agg 3_{fine - tuning}$	0.034 2	0.034 2	72	0.079 6	0.081 3	27	0.038 1	0.039 0	49	0.737 1	0.758 8	7
$Agg 4_{fine - tuning}$	0.043 1	0.043 3	56	0.109 8	0.111 5	22	0.038 1	0.039 0	49	2.656 5	3.116 7	3
$FC 7_{pre - trained}$	0.038 0	0.038 1	65	0.094 6	0.097 3	25	0.043 3	0.044 4	43	1.893 5	3.635 3	4
$FC 6_{pre - trained}$	0.037 7	0.037 8	71	0.079 6	0.081 3	27	0.042 8	0.043 8	46	1.286 7	1.311 3	5
$Agg 1_{pre - trained}$	0.034 2	0.034 2	72	0.079 6	0.081 3	27	0.038 1	0.039 0	49	0.800 2	0.820 2	8
$Agg 2_{pre - trained}$	0.034 2	0.034 2	72	0.079 6	0.081 3	27	0.040 6	0.041 5	48	1.044 4	1.339 5	7
$Agg 3_{pre - trained}$	0.037 9	0.038 0	70	0.079 6	0.081 3	27	0.040 6	0.041 5	48	0.732 0	0.762 7	8
$Agg 4_{pre - trained}$	0.063 8	0.065 6	18	0.263 2	0.261 3	9	0.040 7	0.041 6	46	9.711 4	11.32 4	3