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

作　　者：YANG DongFang SUN FuChun WANG ShiCheng ZHANG JinSheng 

机构地区：[1]The Second Artillery Engineering University [2]State Key Laboratory of Intelligent Technology and Systems, Tsinghua University

出　　处：《Science China(Information Sciences)》2014年第5期268-277,共10页中国科学（信息科学）（英文版）

基　　金：supported by National Natural Science Foundation of China(Grant Nos.2009CB724000,2012CB-821206,61202332,61203354);Tsinghua Self-innovation Project(Grant No.20111081111)

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 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 ego- motion and vehicle-space can be calculated simultaneously. Outdoor experiments are implemented to validate the effectiveness of the proposed approach.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 ego- motion and vehicle-space can be calculated simultaneously. Outdoor experiments are implemented to validate the effectiveness of the proposed approach.

关 键 词：auto navigation monocular vision vehicle distance 

分 类 号：U463.6[机械工程—车辆工程] U495[交通运输工程—载运工具运用工程]