Title :
Radon Transform and Forstner Operator Applying in Buildings Contour Extraction
Author :
Wang Li-Qiang ; Hao Ying
Author_Institution :
Dept. of Comput., Beijing Univ. of Civil Eng. & Archit., Beijing, China
Abstract :
A buildings contour extraction mode, inspired by Radon transform and Forstner operator, is presented. Firstly, the edge is detected from the image and is transformed into polar coordinates by Radon transform. Then using Forstner operator these peaks in the parameter space are found. Finally, building contour is detected through inverse Radon transform. As the experimental results show that the new method is very efficient in reducing noise and locating the edge of building far more precisely.
Keywords :
Radon transforms; edge detection; Forstner operator; buildings contour extraction; edge detection; edge location; inverse Radon transform; noise reduction; Buildings; Computer vision; Data mining; Discrete transforms; Extraterrestrial measurements; Geophysical measurements; Holography; Image edge detection; Noise reduction; Optical interferometry; Contour extraction; Forsmer operator; Radon transform; peaking value measuremen;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery, 2009. FSKD '09. Sixth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3735-1
DOI :
10.1109/FSKD.2009.244