Department of Electrical Engineering (ISY)

Fast and Accurate Ego-Motion Estimation

Johan Hedborg, Per-Erik Forssén
SSBA09
Proceedings SSBA'09 Symposium on Image Analysis
Pages 69-72
March 2009

Abstract

This paper describes a system that efficiently uses the KLT tracker together with a calibrated 5-point solver for structure-from-motion(SfM). Our system uses a GPU to perform tracking, and the CPU for SfM. In this setup, it is advantageous to run the tracker both forwards and backwards in time, to detect incorrectly tracked points. We introduce a modification to the point selection inside the RANSAC step of the 5-point solver, and demonstrate how this speeds up the algorithm. Our evaluations are done using both real camera sequences, and data from a state-of-the art rendering engine with associated ground-truth.

---

Bibtex entry

@inproceedings{hedborg09a,
  author = {Johan Hedborg and Per-Erik Forss{\'e}n},
  title = {{Fast and Accurate Ego-Motion Estimation}},
  booktitle = {Proceedings {SSBA'09} Symposium on Image Analysis},
  year = {2009},
  month = {March},
  pages = {69--72},
}