Pose Estimation for Vehicle-mounted Cameras via Horizontal and Vertical Planes
This work addresses incremental improvements in pose estimation for vehicle-mounted cameras, potentially benefiting autonomous driving and robotics applications.
The authors tackled the problem of estimating camera egomotion from a single affine correspondence by proposing two novel solvers that recover special homographies for horizontal and vertical planes, resulting in methods that are more accurate or comparable to traditional algorithms and faster in robust estimators.
We propose two novel solvers for estimating the egomotion of a calibrated camera mounted to a moving vehicle from a single affine correspondence via recovering special homographies. For the first class of solvers, the sought plane is expected to be perpendicular to one of the camera axes. For the second class, the plane is orthogonal to the ground with unknown normal, e.g., it is a building facade. Both methods are solved via a linear system with a small coefficient matrix, thus, being extremely efficient. Both the minimal and over-determined cases can be solved by the proposed methods. They are tested on synthetic data and on publicly available real-world datasets. The novel methods are more accurate or comparable to the traditional algorithms and are faster when included in state of the art robust estimators.