A Two-Stage Optimization Strategy for Fuzzy Object-Based Analysis Using Airborne LiDAR and High-Resolution Orthophotos for Urban Road Extraction
Table 1
Selected features via PSO used for classification.
Property
Quantifiable attribute
Description/mathematical formulation
Spectral attributes
Height
nDSM
Color
Spectral bands of aerial orthophoto
Digital number of blue, green, and red bands
Spatial attributes
Elongated shapes
Elongation index
, where and are the area and the perimeter of image object
Smooth objects
Shape index
, where is the shape index, is the border length, and is the area of the image object
Distribution of pixels in space
Density
Calculated by the area of the object divided by the approximated average of the major and minor axes of the ellipse fitted to the object
Rectangular shape
Rectangular fit
Describes the difference between a master rectangle and the considered object using the same measure of area, width, and length for the master rectangle ( = complete fitting object, = no fit)