FMD Stereo SLAM: Fusing MVG and Direct Formulation Towards Accurate and Fast Stereo SLAM

FMD Stereo SLAM:融合MVG和直接方法,实现准确,快速的双目SLAM

Fulin Tang, Heping Li, Yihong Wu

We propose a novel stereo visual SLAM framework considering both accuracy and speed at the same time. The framework makes full use of the advantages of key-feature based multiple view geometry(MVG)and direct-based formulation. At the front-end, our system performs direct formulation and constant motion model to predict a robust initial pose, reprojects local map to find 3D-2D correspondence and finally refines pose by the reprojection error minimization. This frontend process makes our system faster. At the back-end, MVG is used to estimate 3D structure. When a new keyframe is inserted, new mappoints are generated by triangulating. In order to improve the accuracy of the proposed system, bad mappoints are removed and a global map is kept by bundle adjustment. Especially, the stereo constraint is performed to optimize the map. This back-end process makes our system more accurate. Experimental evaluation on EuRoC dataset shows that the proposed algorithm can run at more than 100 frames per second on a consumer computer while achieving highly competitive accuracy.

我们提出了一种新颖的双目视觉SLAM框架,同时兼顾了精度和速度。该框架充分利用了基于关键特征的多视图几何(MVG)和基于直接方法的优势。在前端,我们的系统执行直接公式和恒定运动模型来预测稳健的初始姿势,重新投影局部地图以找到3D-2D对应,并通过重投影误差最小化来最终确定姿势。这个前端过程使我们的系统更快。 在后端,MVG用于估计3D结构。 插入新关键帧时,通过三角测量生成新的地图点。为了提高所提出系统的准确性,删除了坏的地图点并通过束调整保持全局地图。 特别地,执行立体约束以优化地图。这种后端流程使我们的系统更加准确。 对EuRoC数据集的实验评估表明,所提出的算法可以在消费者计算机上以每秒100帧以上的速度运行,同时实现高度竞争的准确性。

泡泡一分钟:FMD Stereo SLAM: Fusing MVG and Direct Formulation Towards Accurate and Fast Stereo SLAM的更多相关文章

  1. SLAM到底是什么?一文带你读懂SLAM

    SLAM是Simultaneous localization and mapping缩写,意为“同步定位与建图”,主要用于解决机器人在未知环境运动时的定位与地图构建问题,为了让大家更多的了解SLAM, ...

  2. 泡泡一分钟:Cubic Range Error Model for Stereo Vision with Illuminators

    Cubic Range Error Model for Stereo Vision with Illuminators 带有照明器的双目视觉的三次范围误差模型 "链接:https://pan ...

  3. 泡泡一分钟:Fast and Robust Initialization for Visual-Inertial SLAM

    张宁  Fast and Robust Initialization for Visual-Inertial SLAM链接:https://pan.baidu.com/s/1cdkuHdkSi9x7l ...

  4. 泡泡一分钟:Topomap: Topological Mapping and Navigation Based on Visual SLAM Maps

    Topomap: Topological Mapping and Navigation Based on Visual SLAM Maps Fabian Bl¨ochliger, Marius Feh ...

  5. 泡泡一分钟:Tightly-Coupled Aided Inertial Navigation with Point and Plane Features

    Tightly-Coupled Aided Inertial Navigation with Point and Plane Features 具有点和平面特征的紧密耦合辅助惯性导航 Yulin Ya ...

  6. 泡泡一分钟:BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving

    BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving BLVD:构建自主驾驶的大规模5D语义基准 Jia ...

  7. 泡泡一分钟:GEN-SLAM - Generative Modeling for Monocular Simultaneous Localization and Mapping

    张宁  GEN-SLAM - Generative Modeling for Monocular Simultaneous Localization and Mapping GEN-SLAM  - 单 ...

  8. 泡泡一分钟:Project AutoVision - Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System

    Project AutoVision - Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Cam ...

  9. 泡泡一分钟:Semi-Dense Visual-Inertial Odometry and Mapping for Quadrotors with SWAP Constraints

    张宁 Semi-Dense Visual-Inertial Odometry and Mapping for Quadrotors with SWAP Constraints 具有SWAP约束的四旋翼 ...

随机推荐

  1. redis的过期策略都有哪些?内存淘汰机制都有哪些?手写一下LRU代码实现?

    redis的过期策略都有哪些? 设置过期时间: set key 的时候,使用expire time,就是过期时间.指定这个key比如说只能存活一个小时?10分钟?指定缓存到期就会失效. redis的过 ...

  2. 《你说对就队》第九次团队作业:【Beta】Scrum meeting 1

    <你说对就队>第九次团队作业:[Beta]Scrum meeting 1 项目 内容 这个作业属于哪个课程 [教师博客主页链接] 这个作业的要求在哪里 [作业链接地址] 团队名称 < ...

  3. Vue钩子函数

    Vue的生命周期函数 beforeCreate:function(){ console.log('1-beforeCreate 初始化之后'); }, created:function(){ cons ...

  4. Kubernetes 基本概念介绍

    什么是Kubernetes? Kubernetes(k8s)是自动化容器操作的开源平台,这些操作包括部署,调度和节点集群间扩展. 如果你曾经用过Docker容器技术部署容器,那么可以将Docker看成 ...

  5. Mac上搭建Python集成环境

    Jenkins安装 第一种方式下载安装包 官网 https://jenkins.io/download/ 下载安装包 第二种通过homebrew安装,前提需要安装jdk(推荐) brew instal ...

  6. house买房原理,2019,第一版

    ,购买框架 1,通过自己的买房预算金额 和 pre-approval 确定你要的房屋总价, 估计到自己可以接受的房子,卖方也喜欢这样的买家,但不一定能拿全额贷款 2,pre-approval对信用分数 ...

  7. mongoDB sh.status() too many chunks to print

    too many chunks to print, use verbose if you want to force print 想要看到详细的信息则需要执行: mongos> sh.statu ...

  8. am335x using brctl iptables dhcpcd make multi wan & multi lan network(十五)

    构建多LAN口多WAN口动态网络 [目的] 在AM335X定制动态网络功能,如下所示,在系统当中有两个以太网口,有4G模块,有wifi芯片8188eu支持AP+STA功能. [实验环境] 1.  Ub ...

  9. (11)打鸡儿教你Vue.js

    表单 v-model 指令在表单控件元素上创建双向数据绑定 <div id="app"> <p>单个复选框:</p> <input typ ...

  10. 2019暑期金华集训 Day7 动态规划

    自闭集训 Day7 动态规划 LOJ6395 首先发现这个树的形态没啥用,只需要保证度数之和是\(2n-2\)且度数大于0即可. 然后设\(dp_{i,j}\)表示前\(i\)个点用了\(j\)个度数 ...