Many emerging applications in the field of assisted and autonomous driving rely on accurate position information. Satellite-based positioning is not always sufficiently reliable and accurate for these tasks. Visual odometry can provide a solution to some of these shortcomings. Current systems mainly focus on the use of stereo cameras, which are impractical for large-scale application in consumer vehicles due to their reliance on accurate calibration. Existing monocular solutions on the other hand have significantly lower accuracy. In this paper, we present a novel monocular visual odometry method based on the robust tracking of features in the ground plane. The key concepts behind the method are the modeling of the uncertainty associated with the inverse perspective projection of image features and a parameter space voting scheme to find a consensus on the vehicle state among tracked features. Our approach differs from traditional visual odometry methods by applying 2D scene and motion constraints at the lowest level instead of solving for the 3D pose change. Evaluation both on the public KITTI benchmark and our own dataset show that this is a viable approach for visual odometry which outperforms basic 3D pose estimation due to the exploitation of the largely planar structure of road environments.
展开▼
