Fast and Accurate Ego-Motion Estimation
2009 (English)Conference paper (Refereed)
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.
Place, publisher, year, edition, pages
2009. 69-72 p.
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-50622OAI: oai:DiVA.org:liu-50622DiVA: diva2:271773
Swedish Symposium on Image Analysis - SSBA'2009, March 18-20, Halmstad, Sweden