Extended Hough transform for linear feature detection

Improving the accuracy of line segment detection reduces the complexity of subsequent high-level processing common in cartographic feature detection. We developed a new extension to the Hough transform and reported on its application to building extraction. We expanded the Hough space by a third parameter, the horizontal or vertical coordinate of the image space, to provide incremental information as to the length of the lineal feature being sought. Using this extended HT transform allowed us to more accurately detect the true length of a line segment. In addition, we used a Bayesian probabilistic approach to process our extended Hough space that further increased the accuracy of our extended Hough transform.

[1]  Kazuhito Murakami,et al.  High speed line detection by Hough transform in local area , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[2]  Rufus H. Cofer,et al.  Lineal Feature Detection Using Multi-resolution Wavelet Filters , 2005 .

[3]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[4]  Mark Sandler,et al.  Performance improvements to the Hough transform , 1990 .

[5]  Mohammed Atiquzzaman,et al.  Complete line segment description using the Hough transform , 1994, Image Vis. Comput..

[6]  Helene Oriot,et al.  Extraction of industrial buildings from stereoscopic airborne radar images , 2002, SPIE Remote Sensing.

[7]  Chung-Lin Huang,et al.  Hough transform modified by line connectivity and line thickness , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  J. Shan,et al.  CLASS-GUIDED BUILDING EXTRACTION FROM IKONOS IMAGERY , 2003 .

[9]  Mohammed Atiquzzaman,et al.  A Robust Hough Transform Technique for Complete Line Segment Description , 1995, Real Time Imaging.

[10]  Clark F. Olson,et al.  A General Method for Geometric Feature Matching and Model Extraction , 2001, International Journal of Computer Vision.

[11]  Yerach Doytsher,et al.  MONOCULAR RIGHT-ANGLE BUILDING HYPOTHESIS GENERATION IN REGULARIZED URBAN AREAS BY POSE CLUSTERING , 2003 .

[12]  Hon Fung Li,et al.  Improvements and systolic implementation of the hough transformation for straight line detection , 1989, Pattern Recognit..

[13]  Mohammed Atiquzzaman,et al.  Determination of line length using Hough transform , 1992 .

[14]  David P. Casasent,et al.  Extracting input-line position from Hough transform data. , 1991, Applied optics.

[15]  Ayman Habib,et al.  Line-based Modified Iterated Hough Transform for autonomous single-photo resection , 2003 .

[16]  Shiu Yin Yuen,et al.  Connective hough transform , 1993, Image Vis. Comput..

[17]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[18]  V. F. Leavers,et al.  Which Hough transform , 1993 .

[19]  Thomas Risse,et al.  Hough transform for line recognition: Complexity of evidence accumulation and cluster detection , 1989, Comput. Vis. Graph. Image Process..

[20]  Raymond K. K. Yip,et al.  Line Patterns Hough Transform for line segment detection , 1994, Proceedings of TENCON'94 - 1994 IEEE Region 10's 9th Annual International Conference on: 'Frontiers of Computer Technology'.

[21]  M. Carter.  Computer graphics: Principles and practice , 1997 .

[22]  Samuel P. Kozaitis,et al.  Imagery chain assessment for feature extraction , 2003, SPIE Defense + Commercial Sensing.

[23]  Yi-Hsing Tseng,et al.  SEMIAUTOMATED BUILDING EXTRACTION BASED ON CSG MODEL-IMAGE FITTING , 2003 .

[24]  Julio Villalba,et al.  A fast Hough transform for segment detection , 1995, IEEE Trans. Image Process..