Contribution to the determination of vanishing points using Hough transform
- 1 April 1994
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 16 (4) , 430-438
- https://doi.org/10.1109/34.277598
Abstract
We propose a method to locate three vanishing points on an image, corresponding to three orthogonal directions of the scene. This method is based on two cascaded Hough transforms. We show that, even in the case of synthetic images of high quality, a naive approach may fail, essentially because of the errors due to the limitation of the image size. We take into account these errors as well as errors due to detection inaccuracy of the image segments, and provide a method efficient, even in the case of real complex scenes.Keywords
This publication has 11 references indexed in Scilit:
- A survey of the hough transformPublished by Elsevier ,2005
- Contribution to the determination of vanishing points using Hough transformPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Evaluation of quantization error in computer visionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- Determining perspective structures using hierarchical Hough transformPattern Recognition Letters, 1989
- Natural representations for straight lines and the Hough transform on discrete arraysPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Contribution to the Prediction of Performances of the Hough TransformPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- Determining vanishing points from perspective imagesComputer Vision, Graphics, and Image Processing, 1984
- Interpreting perspective imagesArtificial Intelligence, 1983
- Inherent Bias and Noise in the Hough TransformPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1983
- Transformations for the Computer Detection of Curves in Noisy PicturesComputer Graphics and Image Processing, 1975