Fast, Robust, and Consistent Camera Motion Estimation

Previous algorithms that recover camera motion from image velocities sufferfrom both bias and excessive variance in the results. We propose a robust estimator of camera motion that is statistically consistent when image noise is isotropic. Consistency means that the estimated motion converges in probability to the true value as the number of image points increases. An algorithm based on reweighted Gauss-Newton iterations handles 100 velocity measurements in about 50 milliseconds on a workstation.

• Type: Conference
• Year: 1999
• Where: CVPR
• Authors: Tong Zhang, Carlo Tomasi
• Keywords: Camera Motion, Computer Vision, CVPR 1999, Estimated Motion, Image Points Increases, Image Velocities