Visual odometry based on locally planar ground assumption
Hui Wang, Kui Yuan, Wei Zou, Qingrui Zhou · 2006
A method for estimating ego-motion with vehicle mounted single camera is presented in this paper. Simultaneous translation and rotation are accurately measured by detecting and tracking features in image sequences. This approach is based on locally planar ground assumption and runs in real-time. It has been verified in a variety of real-world environments and on real mobile robot platforms.