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

摘要: 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 monocular camera. First, we introduce an incremental depth parameterized model overcome scale ambiguity problem vision, which differs from other models with reduced state-dimension consistent observability. In addition, view-field camera is divided into static dynamic parts so that egomotion vehicle-space can be calculated simultaneously. Outdoor experiments implemented validate effectiveness proposed approach.