Cascade Convolutional Neural Network Based on Transfer-Learning for Aircraft Detection on High-Resolution Remote Sensing Images

Table 4

Detailed evaluation criteria and comparison for the four detection results.

Test image	Method	FDR (%)	MR (%)	AC (%)	ER (%)
Berlin Tegel Airport	CCNN	5.71	0	100	5.71
	LOGNet-C	7.69	3.23	96.77	10.92
Sydney International Airport	CCNN	6.58	2.56	97.44	9.14
	LOGNet-C	48.54	10.87	89.13	59.41
Tokyo Haneda Airport	CCNN	4.39	3.19	96.81	7.58
	LOGNet-C	20.80	1.54	98.46	22.34