Fast and Accurate Structure and Motion Estimation
Johan Hedborg, Per-Erik Forssén, Michael FelsbergISVC09
International Symposium on Visual Computing
Volume 5875, Pages 211-222
November 2009
Abstract
This paper describes a system for structure-and-motion estimation for real-time navigation and obstacle avoidance. We demonstrate a technique to increase the efficiency of the 5-point solution to the relative pose problem. This is achieved by a novel sampling scheme, where we add a distance constraint on the sampled points inside the RANSAC loop, before calculating the 5-point solution. Our setup uses the KLT tracker to establish point correspondences across time in live video. We also demonstrate how an early outlier rejection in the tracker improves performance in scenes with plenty of occlusions. This outlier rejection scheme is well suited to implementation on graphics hardware. We evaluate the proposed algorithms using real camera sequences with fine-tuned bundle adjusted data as ground truth. To strenghten our results we also evaluate using sequences generated by a state-of-the-art rendering software. On average we are able to reduce the number of RANSAC iterations by half and thereby double the speed.
Full Paper
Portable document format file PDF (
Bibtex entry
@inproceedings{hedborg09b, author = {Johan Hedborg and Per-Erik Forss{\'e}n and Michael Felsberg}, title = {{Fast and Accurate Structure and Motion Estimation}}, booktitle = {International Symposium on Visual Computing}, year = {2009}, month = {November}, series = {Lecture Notes in Computer Science}, volume = {5875}, pages = {211--222}, isbn = {978-3-642-10330-8}, note = {http://dx.doi.org/10.1007/978-3-642-10331-5_20}, publisher = {Springer} }
Per-Erik Forssén
Contact:
Computer Vision Laboratory
Department of Electrical Engineering
Building B
Room 2D:521
SE-581 83 Linköping, Sweden
+46(0)13 285654
< >
My pages:
Informationsansvarig: Per-Erik Forssén
Senast uppdaterad: 2024-09-28