Fusion of vision, 3D gyro and GPS for camera dynamic registration
Fusion of vision, 3D gyro and GPS for camera dynamic registration
复制标题
视觉、3D 陀螺仪和 GPS 融合，实现相机动态配准
DOI：
10.1109/icpr.2004.1334539
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
F. Lamosa
中科院分区：
文献类型：
--
作者：
Zhencheng Hu;K. Uchimura;Hanqing Lu;F. Lamosa
提出了一种新的用于室外导航系统的混合摄像机位姿跟踪系统框架。传统的基于视觉或惯性传感器的解决方案大多是为结构良好的环境而设计的，然而这对于大多数户外不受控制的应用是不可用的。我们的系统结合了视觉，GPS和3D惯性陀螺仪传感器，以获得准确和鲁棒的相机位姿估计结果。融合方法是基于我们的PMM（参数化模型匹配）算法，其中的道路形状模型是从数字地图参考GPS绝对道路位置，并与道路特征提取的真实的图像匹配。惯性数据估计搜索参数的初始状态，并且还用作稳定位姿输出的相对公差。通过不同路况下的真实的道路试验，对本文提出的算法进行了验证。
This paper presents a novel framework of hybrid camera pose tracking system for outdoor navigation system. Traditional vision based or inertial sensor based solutions are mostly designed for well-structured environment, which is however unavailable for most outdoor uncontrolled applications. Our system combines vision, GPS and 3D inertial gyroscope sensors to obtain accurate and robust camera pose estimation result. The fusion approach is based on our PMM (parameterized model matching) algorithm, in which the road shape model is derived from the digital map referring to GPS absolute road position, and matches with road features extracted from the real image. Inertial data estimates the initial state of searching parameters, and also serves as relative tolerance to stable the pose output. The algorithms proposed in this paper are validated with the experimental results of real road tests under different road conditions.