• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>World congress on ITS (Intelligent Transportation Society) >Towards A New Generation of Car Navigation System -Data Fusion Technology in Solving On-board CameraRegistration Problem
【24h】

Towards A New Generation of Car Navigation System -Data Fusion Technology in Solving On-board CameraRegistration Problem

机译：面向新一代汽车导航系统-数据融合技术解决车载摄像头注册问题

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

To properly align objects in the real and virtual world in an Augmented Reality (AR) space,rnit is essential to keep tracking camera's exact 3D position and orientation, which is wellrnknown as the camera registration problem. Traditional vision based or inertial sensor basedrnsolutions are mostly designed for well-structured environment, which is however unavailablernfor outdoor uncontrolled road navigation applications. This paper proposed a hybrid camerarnpose tracking system that combines vision, GPS and 3D inertial gyroscope technologies. Thernfusion approach is based on our PMM (parameterized model matching) algorithm, in whichrnthe road shape model is derived from the digital map referring to GPS absolute road position,rnand matches with road features extracted from the real image. Inertial data estimates the initialrnpossible motion, and also serves as the relative tolerance to stabilize output. The algorithmsrnproposed in this paper are validated with the experimental results of real road tests underrndifferent conditions and types of road.
机译：为了在增强现实（AR）空间中正确对齐现实世界和虚拟世界中的对象，网格对于保持跟踪摄像机的精确3D位置和方向至关重要，这是众所周知的摄像机注册问题。传统的基于视觉或基于惯性传感器的解决方案大多是为结构良好的环境设计的，但是，对于室外不受控制的道路导航应用而言，这是不可用的。本文提出了一种结合了视觉，GPS和3D惯性陀螺仪技术的混合摄像机跟踪系统。融合方法基于我们的PMM（参数化模型匹配）算法，其中道路形状模型是从数字地图中提取的，该数字地图参考GPS绝对​​道路位置，并与从真实图像中提取的道路特征进行匹配。惯性数据估计了可能的初始运动，并且还用作稳定输出的相对公差。本文提出的算法在不同条件和道路类型下的真实道路试验的实验结果进行了验证。

著录项

  • 来源
  • 会议地点 Nagoya(JP)
  • 作者

    Zhencheng Hu; Keiichi Uchimura; Francisco Lamosa;

  • 作者单位

    Computer Science Department, Kumamoto Universityrn2-39-1 Kurokami, Kumamoto, 860-8555 JapanrnTEL(FAX) : +81-96-342-3638 hu@cs.kumamoto-u.ac.jp;

    Computer Science Department, Kumamoto Universityrn2-39-1 Kurokami, Kumamoto, 860-8555 JapanrnTEL(FAX) : +81-96-342-3638 uchimura@cs.kumamoto-u.ac.jp;

    Computer Recognition Systems Ltd.rn1 Roebuck Estate, Binfield, Bracknell, Berkshire RG41 4DG, United KingdomrnTEL : +44-1344-443-463 f.lamosa@computer.org;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号