A fast recursive 3D model reconstruction algorithm for multimedia applications
- 1 January 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10514651) , 241-244 Vol.2
- https://doi.org/10.1109/icpr.2004.1334143
Abstract
A recursive two-step method to recover structure and motion from image sequences based on Kalman filtering is described in this paper. The algorithm consists of two major steps. The first step is an extended Kalman filter for the estimation of the object's pose. The second step is a set of extended Kalman filters, one for each model point, for refining the positions of the model features in the 3D space. The initial guess is a planar model formed under the assumption of orthographic projection on the first image. These two steps alternate from frames to frames. The planar model converges to the final structure as the image sequence is scanned sequentially. The performance of the algorithm is demonstrated with both synthetic data and real world objects. Comparisons with different approaches have been performed and show that our method is more efficient.Keywords
This publication has 8 references indexed in Scilit:
- Simultaneous localization and map-building using active visionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Structure from motion causally integrated over timePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Position and orientation estimation based on Kalman filtering of stereo imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Sequential Updating of Projective and Affine Structure from MotionInternational Journal of Computer Vision, 1997
- Recursive estimation of motion, structure, and focal lengthPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Shape and motion from image streams under orthography: a factorization methodInternational Journal of Computer Vision, 1992
- Recursive 3-D motion estimation from a monocular image sequenceIEEE Transactions on Aerospace and Electronic Systems, 1990
- 3D positional integration from image sequencesImage and Vision Computing, 1988