首页> 美国卫生研究院文献>Micromachines >A Novel Fault-Tolerant Navigation and Positioning Method with Stereo-Camera/Micro Electro Mechanical Systems Inertial Measurement Unit (MEMS-IMU) in Hostile Environment
【2h】

A Novel Fault-Tolerant Navigation and Positioning Method with Stereo-Camera/Micro Electro Mechanical Systems Inertial Measurement Unit (MEMS-IMU) in Hostile Environment

机译:在敌对环境中使用立体相机/微机电系统惯性测量单元(MEMS-IMU)的新型容错导航和定位方法

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

Visual odometry (VO) is a new navigation and positioning method that estimates the ego-motion of vehicles from images. However, VO with unsatisfactory performance can fail severely in hostile environment because of the less feature, fast angular motions, or illumination change. Thus, enhancing the robustness of VO in hostile environment has become a popular research topic. In this paper, a novel fault-tolerant visual-inertial odometry (VIO) navigation and positioning method framework is presented. The micro electro mechanical systems inertial measurement unit (MEMS-IMU) is used to aid the stereo-camera, for a robust pose estimation in hostile environment. In the algorithm, the MEMS-IMU pre-integration is deployed to improve the motion estimation accuracy and robustness in the cases of similar or few feature points. Besides, a dramatic change detector and an adaptive observation noise factor are introduced, tolerating and decreasing the estimation error that is caused by large angular motion or wrong matching. Experiments in hostile environment showing that the presented method can achieve better position estimation when compared with the traditional VO and VIO method.
机译:视觉里程表(VO)是一种新的导航和定位方法,可以根据图像估算车辆的自我运动。但是,性能欠佳的VO在恶劣的环境中可能会严重失败,这是因为其特征少,角度运动快或照明变化大。因此,在恶劣环境中增强VO的鲁棒性已成为热门的研究课题。本文提出了一种新颖的容错视觉惯性里程计(VIO)导航和定位方法框架。微机电系统惯性测量单元(MEMS-IMU)用于辅助立体摄像机,以在恶劣环境中进行可靠的姿态估计。在该算法中,部署了MEMS-IMU预集成,以在特征点相似或很少的情况下提高运动估计的准确性和鲁棒性。此外,还引入了动态变化检测器和自适应观测噪声因子,可以容忍和减少由大角度运动或错误匹配引起的估计误差。在敌对环境中的实验表明,与传统的VO和VIO方法相比,该方法可以获得更好的位置估计。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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