Table 6.

Classification results for PCE Full (MWIR daytime) 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	123	15	27	0	15	2	3	66%	BMP2	283	2	6	1	2	0	0	96%
BRDM2	93	224	7	4	3	8	0	66%	BRDM2	1	194	0	8	50	3	12	72%
BTR70	72	6	158	4	0	6	0	64%	BTR70	3	36	56	16	5	5	4	45%
SUV	29	1	0	244	3	14	0	84%	SUV	0	19	5	13	19	11	12	16%
T72	106	9	0	1	72	3	0	38%	T72	8	70	19	11	68	31	8	32%
Truck	54	0	0	1	0	154	0	74%	Truck	4	8	0	34	32	8	24	7%
ZSU23-4	36	40	9	5	0	28	33	22%	ZSU23-4	0	4	1	5	0	1	221	95%
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	82	2	6	7	7	236	16	23%	BMP2	344	1	0	1	1	5	7	96%
BRDM2	5	330	2	0	0	20	0	92%	BRDM2	1	268	0	57	23	4	6	75%
BTR70	46	0	215	1	7	85	1	61%	BTR70	0	110	104	39	38	7	61	29%
SUV	1	4	0	247	1	68	2	76%	SUV	18	24	4	219	42	24	28	61%
T72	112	35	0	6	179	18	0	51%	T72	11	9	0	67	216	49	7	60%
Truck	3	14	0	12	9	292	10	86%	Truck	20	59	10	116	60	75	19	21%
ZSU23-4	5	76	0	0	15	130	130	37%	ZSU23-4	1	7	9	13	2	5	322	90%
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	87	0	3	10	20	149	9	31%	BMP2	101	0	5	3	6	3	1	85%
BRDM2	39	81	0	0	22	76	13	35%	BRDM2	20	76	1	51	17	3	17	41%
BTR70	5	65	117	0	25	0	97	38%	BTR70	2	16	1	27	10	2	53	1%
SUV	20	14	0	8	66	1	2	7%	SUV	2	7	0	64	27	5	12	55%
T72	4	19	0	0	177	13	17	77%	T72	24	27	5	5	167	17	7	66%
Truck	0	0	0	0	30	78	1	72%	Truck	6	5	0	21	1	5	1	13%
ZSU23-4	0	0	0	0	6	0	329	98%	ZSU23-4	1	19	4	7	13	3	84	64%