Simultaneous estimation of ego-motion and vehicle distance by using a monocular camera

Auto navigation and vehicle distance estimation are of the critical importance in intelligent vehicles. This paper proposes a novel approach to solve these two problems simultaneously by using a monocular camera. First, we introduce an incremental depth parameterized model to overcome the scale ambiguity problem in monocular vision, which differs from other parameterized models with reduced state-dimension and consistent observability. In addition, the view-field of camera is divided into static and dynamic parts so that the egomotion and vehicle-space can be calculated simultaneously. Outdoor experiments are implemented to validate the effectiveness of the proposed approach.