Omnidirectional camera model and epipolar geometry estimation by RANSAC with bucketing

  • Authors:

  • Branislav Mičušík;Tomáš Pajdla

  • Affiliations:

  • Center for Machine Perception, Dept. of Cybernetics, Czech Technical University, Prague, Czech Republic;Center for Machine Perception, Dept. of Cybernetics, Czech Technical University, Prague, Czech Republic

  • Venue:
  • SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a robust method of image points sampling used in ransac for a class of omnidirectional cameras (view angle above 180°) possessing central projection to obtain simultaneous estimation of a camera model and epipolar geometry.We focus on problem arising in ransac based estimation technique for omnidirectional images when the most of correspondences are established near the center of view field. Such correspondences satisfy the camera model for almost any degree of an image formation non-linearity. They are often selected in ransac as inliers, estimation stops prematurely, the most informative points near the border of the view field are not used, and incorrect camera model is estimated. We show that a remedy to this problem is achieved by not using points near the center of the view field circle for camera model estimation and controlling the points sampling in ransac. The camera model estimation is done from image correspondences only, without any calibration objects or any assumption about the scene except for rigidity. We demonstrate our method in real experiments with high quality but cheap and widely available Nikon FC-E8 fish-eye lens.