DAVIS第六课: 基于关键帧的非线性优化的事件相机实时VIO算法

9 篇文章 195 订阅 ¥19.90 ¥99.00
本文介绍了使用关键帧的非线性优化实现实时视觉惯性里程计(VIO)的方法,尤其适用于事件相机。通过对事件帧的特征检测、跟踪,结合IMU数据进行非线性优化,提高了在高挑战场景下的运动估计精度。通过Schur补边缘化技术处理旧关键帧,以保持系统效率并保留有用信息。
摘要由CSDN通过智能技术生成

学习论文Real-time Visual-Inertial Odometry for Event Cameras using Keyframe-based Nonlinear Optimization

1. 摘要

提出一种新颖, 精确的紧密耦合的视觉里程计。充分利用该相机的属性去估计相机的在高挑战场景下的运动。

这个方法追踪一组特征点(在图像平面提取的特征), 我们考虑时空重叠窗口内的事件, 用当前相机的运动和场景结构进行校准, 产生运动补偿帧。

最后结合基于关键帧内追踪到的特征点,基于非线性优化的VO算法去估计相机的6-自由度位姿, 速度和IMU偏差。

2.方法

  • Feature Detectiong

对运动消除的之后的事件帧采用Fast角点检测,github项目地址为: https://github.com/uzh-rpg/fast

 Fast Cornel detection[23]:  Machine learning for high-speed corner detection. Edward Rosten
  • Feature Tracking and LandMarks

相邻两事件帧使用金字塔LK光流法去追踪路标点, IMU获取的转换矩阵用于预测特征的位置, 使用金字塔跟踪的位姿进行校准, 对那些没有追踪成功的点立即丢弃。

pyramidal Lukas-Kanade [2] : Lucas-kanade 20 years on: A unifying fra
  • 1
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 3
    评论
Combining visual and inertial measurements has become popular in mobile robotics, since the two sensing modalities offer complementary characteristics that make them the ideal choice for accurate Visual-Inertial Odometry or Simultaneous Localization and Mapping (SLAM). While historically the problem has been addressed with filtering, advancements in visual estimation suggest that non-linear optimization offers superior accuracy, while still tractable in complexity thanks to the sparsity of the underlying problem. Taking inspiration from these findings, we formulate a rigorously probabilistic cost function that combines reprojection errors of landmarks and inertial terms. The problem is kept tractable and thus ensuring real-time operation by limiting the optimization to a bounded window of keyframes through marginalization. Keyframes may be spaced in time by arbitrary intervals, while still related by linearized inertial terms. We present evaluation results on complementary datasets recorded with our custom-built stereo visual-inertial hardware that accurately synchronizes accelerometer and gyroscope measurements with imagery. A comparison of both a stereo and monocular version of our algorithm with and without online extrinsics estimation is shown with respect to ground truth. Furthermore, we compare the performance to an implementation of a state-of-the-art stochasic cloning sliding-window filter. This competititve reference implementation performs tightly-coupled filtering-based visual-inertial odometry. While our approach declaredly demands more computation, we show its superior performance in terms of accuracy.
评论 3
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

爱发呆de白菜头

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值