Table A3.

Classification results for PCE 50 (optical video) case. Left shows the confusion matrix and the last column shows the classification accuracy.

1000 m									2500 m
Vehicles	BMP2	BRDM2	BTR70	SUV	T72	Truck	ZSU23-4	Accuracy	Vehicles	BMP2	BRDM2	BTR70	SUV	T72	Truck	ZSU23-4	Accuracy
BMP2	23	0	71	30	105	13	40	8%	BMP2	0	0	0	0	0	0	0	0%
BRDM2	0	39	1	90	5	142	0	14%	BRDM2	0	0	0	0	0	0	0	0%
BTR70	0	0	244	26	21	20	1	84%	BTR70	0	0	0	0	0	0	0	0%
SUV	0	0	0	120	0	173	0	41%	SUV	0	0	0	0	0	0	0	0%
T72	0	0	7	39	251	35	3	75%	T72	0	0	0	0	0	0	0	0%
Truck	0	3	8	52	13	220	1	75%	Truck	0	0	0	0	0	0	0	0%
ZSU23-4	0	0	0	42	16	21	203	72%	ZSU23-4	0	0	0	0	0	0	0	0%
1500 m									3000 m
Vehicles	BMP2	BRDM2	BTR70	SUV	T72	Truck	ZSU23-4	Accuracy	Vehicles	BMP2	BRDM2	BTR70	SUV	T72	Truck	ZSU23-4	Accuracy
BMP2	52	0	99	47	157	5	14	14%	BMP2	0	0	0	0	1	0	0	0%
BRDM2	0	27	36	82	25	173	16	8%	BRDM2	0	0	0	0	0	9	0	0%
BTR70	0	0	344	1	28	0	1	92%	BTR70	0	0	0	0	20	0	0	0%
SUV	0	0	0	126	1	246	0	34%	SUV	0	0	0	0	0	0	0	0%
T72	0	0	36	6	326	5	0	87%	T72	0	0	0	0	2	0	0	100%
Truck	0	4	25	5	45	284	10	76%	Truck	0	0	0	0	4	0	0	0%
ZSU23-4	0	0	26	1	125	7	215	57%	ZSU23-4	0	0	0	0	15	0	0	0%
2000 m									3500 m
Vehicles	BMP2	BRDM2	BTR70	SUV	T72	Truck	ZSU23-4	Accuracy	Vehicles	BMP2	BRDM2	BTR70	SUV	T72	Truck	ZSU23-4	Accuracy
BMP2	6	0	105	127	48	69	0	2%	BMP2	0	0	0	0	0	0	0	0%
BRDM2	0	0	3	1	2	13	0	0%	BRDM2	0	0	0	0	0	0	0	0%
BTR70	0	0	293	12	8	36	0	84%	BTR70	0	0	0	0	0	0	0	0%
SUV	0	0	5	23	7	200	0	10%	SUV	0	0	0	0	0	0	0	0%
T72	0	0	12	130	79	127	0	23%	T72	0	0	0	0	0	0	0	0%
Truck	1	1	23	5	42	156	0	68%	Truck	0	0	0	0	0	0	0	0%
ZSU23-4	0	0	87	47	106	93	3	1%	ZSU23-4	0	0	0	0	0	0	0	0%