Motion Estimation for Self-Driving Cars with a Generalized Camera
Authors:
- Gim Hee LeeGLGim Hee Lee
- Friedrich FaundorferFFFriedrich Faundorfer
- Marc PollefeysMPMarc Pollefeys
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2746-2753
Abstract
In this paper, we present a visual ego-motion estimation algorithm for a self-driving car equipped with a close-to-market multi-camera system. By modeling the multi-camera system as a generalized camera and applying the non-holonomic motion constraint of a car, we show that this leads to a novel 2-point minimal solution for the generalized essential matrix where the full relative motion including metric scale can be obtained. We provide the analytical solutions for the general case with at least one inter-camera correspondence and a special case with only intra-camera correspondences. We show that up to a maximum of 6 solutions exist for both cases. We identify the existence of degeneracy when the car undergoes straight motion in the special case with only intra-camera correspondences where the scale becomes unobservable and provide a practical alternative solution. Our formulation can be efficiently implemented within RANSAC for robust estimation. We verify the validity of our assumptions on the motion model by comparing our results on a large real-world dataset collected by a car equipped with 4 cameras with minimal overlapping field-of-views against the GPS/INS ground truth.Keywords
This publication has 11 references indexed in Scilit:
- Real-time 6D stereo Visual Odometry with non-overlapping fields of view2012
- Absolute scale in structure from motion from a single vehicle mounted camera by exploiting nonholonomic constraints2009
- Real-time monocular visual odometry for on-road vehicles with 1-point RANSAC2009
- Speeded-Up Robust Features (SURF)Computer Vision and Image Understanding, 2008
- Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems2008
- Fast iterative alignment of pose graphs with poor initial estimates2006
- Multi-View Geometry for General Camera Models2005
- An efficient solution to the five-point relative pose problemIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Multiple View Geometry in Computer Vision2004
- Using many cameras as one2003