Radial Casting Algorithm for Extraction of Man-Made Features from High Resolution Digital Satellite Imagery

The extraction of man-made features from high resolution digital satellite imagery is an important step to underpin management geo-information in any country. Man-made and buildings particular are required for various applications such as urban planning, creation geographic information systems databases generation models. Manual processes expensive, labor intensive, need well trained personnel cannot cope with demand changing environment. This paper, presents a Radial Casting Algorithm (RCA) used extract imagery. algorithm measures only single point on approximate center the building image fine measurement automatically determined. modification original snakes model developed by Kass et al whereby external constraints energy term removed which negatively affects convergence properties contour provide ability snake variability image. was tested three areas different quantitative were employed evaluate accuracy, efficiency capability shows that time extracting reduced 32 percent, rate 92 percent Area coverage extracted polygons 98 percent.