Vanishing point detection without any a priori information

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 25; no. 4; pp. 502 - 507
• Main Authors: Almansa, A., Desolneux, A., Vamech, S.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2003; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; Calibration; Cameras; Computer Science; Computer vision; Computer Vision and Pattern Recognition; Detection algorithms; Detectors; Digital cameras; Digital images; H infinity control; Image Processing; Intelligence; Layout; Mathematics; Meeting planning; Parallel processing; Pattern analysis; Statistics; Three dimensional; Tuning; line grouping; false alarms; Helmoltz principle; parallel lines; computer vision; 3D scene; vanishing point detection; line detection; calibration; camera calibration parameters
• ISSN: 0162-8828; 1939-3539
• DOI: 10.1109/TPAMI.2003.1190575

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.