A Two-Stage Optimization Strategy for Fuzzy Object-Based Analysis Using Airborne LiDAR and High-Resolution Orthophotos for Urban Road Extraction

Table 5

Classification assessment (confusion matrix, per class accuracies, and total accuracies) on the study area used for method development.

User class/sample	Building	Road	Tree	Grass	Bare	Water	Shadow	Sum
Confusion matrix
Building	65	0	0	0	7	0	0	72
Road	2	59	1	8	10	0	1	81
Tree	1	0	68	2	0	0	1	72
Grass	0	0	1	23	5	1	1	31
Bare	7	7	0	2	66	0	0	82
Water	0	0	0	0	0	4	0	4
Shadow	0	0	5	1	0	0	24	30
Sum	76	66	75	36	88	5	27
Accuracy
Producer	0.85	0.89	0.90	0.63	0.75	0.80	0.88
User	0.90	0.72	0.94	0.74	0.80	1	0.80
KIA per class	0.82	0.86	0.88	0.60	0.68	0.80	0.88
Overall accuracy (%)
82
Kappa index of agreement (KIA)
0.79