Vanishing point detection without any a priori information

Almansa, A; Desolneux, A; Vamech, S

doi:10.1109/TPAMI.2003.1190575

by A Almansa, A Desolneux, S Vamech

Abstract:

Even though vanishing points in digital images result from parallel lines in the 3D scene, most of the proposed detection algorithms are forced to rely heavily either on additional properties (like orthogonality or coplanarity and equal distance) of the underlying 3D lines, or on knowledge of the camera calibration parameters, in order to avoid spurious responses. In this work, we develop a new detection algorithm that relies on the Helmoltz principle recently proposed for computer vision by Desolneux et al (2001; 2003), both at the line detection and line grouping stages. This leads to a vanishing point detector with a low false alarms rate and a high precision level, which does not rely on any a priori information on the image or calibration parameters, and does not require any parameter tuning.

View PDF

Reference:

Vanishing point detection without any a priori information (A Almansa, A Desolneux, S Vamech), In IEEE Transactions on Pattern Analysis and Machine Intelligence, Published by the IEEE Computer Society, volume 25, 2003.

Bibtex Entry:

@article{Almansa2003,
	Abstract = {Even though vanishing points in digital images result from parallel lines in the 3D scene, most of the proposed detection algorithms are forced to rely heavily either on additional properties (like orthogonality or coplanarity and equal distance) of the underlying 3D lines, or on knowledge of the camera calibration parameters, in order to avoid spurious responses. In this work, we develop a new detection algorithm that relies on the Helmoltz principle recently proposed for computer vision by Desolneux et al (2001; 2003), both at the line detection and line grouping stages. This leads to a vanishing point detector with a low false alarms rate and a high precision level, which does not rely on any a priori information on the image or calibration parameters, and does not require any parameter tuning.},
	Author = {Almansa, A and Desolneux, A and Vamech, S},
	Doi = {10.1109/TPAMI.2003.1190575},
	Issn = {0162-8828},
	Journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
	Month = {apr},
	Number = {4},
	Pages = {502--507},
	Publisher = {Published by the IEEE Computer Society},
	Title = {{Vanishing point detection without any a priori information}},
	Url = {http://www.math-info.univ-paris5.fr/{~}desolneux/papers/vpoint03.pdf},
	Volume = {25},
	Year = {2003},
	Bdsk-Url-1 = {http://www.math-info.univ-paris5.fr/%7B~%7Ddesolneux/papers/vpoint03.pdf},
	Bdsk-Url-2 = {https://doi.org/10.1109/TPAMI.2003.1190575}}