Camera calibration using spheres: A semi-definite programming approach

• Authors: Motilal Agrawal;Larry S. Davis
• Venue: ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
• Year: 2003

Vision algorithms utilizing camera networks with a commonfield of view are becoming increasingly feasible andimportant. Calibration of such camera networks is a challengingand cumbersome task. The current approaches forcalibration using planes or a known 3D target may not befeasible as these objects may not be simultaneously visiblein all the cameras. In this paper, we present a new algorithmto calibrate cameras using occluding contours of spheres.In general, an occluding contour of a sphere projects to anellipse in the image. Our algorithm uses the projection ofthe occluding contours of three spheres and solves for theintrinsic parameters and the locations of the spheres. Theproblem is formulated in the dual space and the parametersare solved for optimally and efficiently using semi-definiteprogramming. The technique is flexible, accurate and easyto use. In addition, since the contour of a sphere is simultaneouslyvisible in all the cameras, our approach cangreatly simplify calibration of multiple cameras with a commonfield of view. Experimental results from computer simulateddata and real world data, both for a single cameraand multiple cameras, are presented.