On the Building Feature Extraction from Aerial Image with Orientation Constrained Hough Transformation
Kuen-Tzung Chang* Wei-Hsin Ho** Tian-Yuan Shih***1
Abstract
Hough Transform is an effective method for extracting geometric primitives from image. However, the standard scheme suffers from the correlated error when the image content is complex. In this study, the orientation constrained Hough transform is proposed for the extraction of building edges from the scanned aerial photo. Based on the chain code concept, twelve templates are defined for the screening of line components to reduce the range of the parameter space. This procedure reduces the number of transformations required, and also limits the influence of the correlated error. Numerical experiments are performed with both the standard Hough transform and the proposed scheme. Three robustness indices, SNR, and the execution time are computed for evaluation.
Keywords:
Geometric Primitives, Orientation Constrained Hough Transform, Man-made Features
*Ph.D Student, Department of Civil Engineering, National Chiao Tung University.
**Associate Professor, Department of Land Economics, National Cheng Chi University.
***Professor, Department of Civil Engineering, National Chiao Tung University
1Author to whom correspondence should be addressed. Phone no. :03-5712121 ext. 54940.