Fast vanishing points detection for omnidirectional images

Duan, Wenting and Allinson, Nigel (2012) Fast vanishing points detection for omnidirectional images. In: Second International Conference, CMSP 2012, December 7-9 2012, Shanghai, China.

Full content URL:

Full text not available from this repository.

Item Type:Conference or Workshop contribution (Presentation)
Item Status:Live Archive


This paper presents a novel method for extracting the dominant vanishing directions from omnidirectional images using the detected conics and lines. The method assumes the camera system has vertically aligned optical axis and is partially calibrated, i.e. only mirror parameter and FOV are known. Based on the geometric properties of catadioptric line projection, the algorithm fully recovers the other camera calibration parameters, cluster the detected conics and use the conic intersections to derive the vanishing points (VPs). The approach shows applying certain geometric constraints can enable fast conic grouping and VPs detection. The efficiency of our method has been validated by experiments on real images (publicly available).

Additional Information:Communications in Computer and Information Science
Keywords:Vanishing points, conic detection and grouping, catadioptric camera, calibration
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:8298
Deposited On:25 Mar 2013 09:35

Repository Staff Only: item control page