ORB-SLAM2：多模态SLAM系统实现实时定位与建图

需积分: 14 200 浏览量更新于2024-09-09 收藏 3.93MB PDF 举报

ORB-SLAM2是由Raúl Mur-Artal和Juan D. Tardós开发的一款全面的视觉SLAM（同时定位与映射）系统，旨在支持单目、双目和RGB-D相机在各种环境中的实时操作。该系统设计初衷是为用户提供一个开源工具，无论是在小型手持室内场景，还是无人机在工业环境或车辆在城市驾驶中的应用，都能在标准CPU上实现高效运行。核心特点包括： 1. 模块化设计：ORB-SLAM2采用了模块化的结构，可以适应不同类型的相机输入，如单目视觉（仅依赖于图像的特征点）、立体视觉（通过左右眼图像的对比）以及RGB-D（融合了深度信息）。 2. 地图重用与环路闭合：系统具备地图重用功能，当重新访问之前探索过的区域时，可以利用已有的地图信息进行快速定位和导航。同时，通过高效的环路闭合算法，系统能够识别和关联先前的航迹，进一步提高定位精度和鲁棒性。 3. 后端优化：基于束调整（Bundle Adjustment）的后端处理，结合单目和立体视觉观测，提供了高精度的路径估计，包括尺度准确性。这种优化技术确保了在长时间运行和大规模数据集上的稳定性能。 4. 轻量级定位模式：为了应对未被映射区域，ORB-SLAM2引入了一种视觉里程计（Visual Odometry）驱动的轻量级定位方法。这种方法利用视觉线索跟踪来维持无漂移的定位，并在必要时匹配到地图点，实现零漂移定位。 5. 评估与性能：经过在29个公开数据集上的评估，ORB-SLAM2展示了业界领先的定位精度，在大多数情况下是最佳的SLAM解决方案。其开源代码不仅对SLAM社区有极大价值，也为其他领域的研究人员提供了一个现成的SLAM研究平台。 ORB-SLAM2是一款功能强大且易于使用的SLAM系统，它不仅关注高精度定位，还注重跨平台兼容性和实用性，对于需要在视觉导航和机器人定位领域进行研究或应用的用户来说，具有很高的实用性和参考价值。

ORB-SLAM2: an Open-Source SLAM System for

Monocular, Stereo and RGB-D Cameras

ul Mur-Artal and Juan D. Tard

Abstract— We present ORB-SLAM2 a complete SLAM sys-

tem for monocular, stereo and RGB-D cameras, including

map reuse, loop closing and relocalization capabilities. The

system works in real-time in standard CPUs in a wide variety

of environments from small hand-held indoors sequences, to

drones ﬂying in industrial environments and cars driving

around a city. Our backend based on Bundle Adjustment

with monocular and stereo observations allows for accurate

trajectory estimation with metric scale. Our system includes

a lightweight localization mode that leverages visual odometry

tracks for unmapped regions and matches to map points that

allow for zero-drift localization. The evaluation in 29 popular

public sequences shows that our method achieves state-of-the-

art accuracy, being in most cases the most accurate SLAM

solution. We publish the source code, not only for the beneﬁt

of the SLAM community, but with the aim of being an out-of-

the-box SLAM solution for researchers in other ﬁelds.

I. INTRODUCTION

Simultaneous Localization and Mapping (SLAM) has been

a hot research topic in the last two decades in the Computer

Vision and Robotics communities, and has recently attracted

the attention of high-technological companies. SLAM tech-

niques build a map of an unknown environment and localize

the sensor in the map with a strong focus on real-time

operation. Among the different sensor modalities, cameras

are cheap and provide rich information of the environment

that allows for robust and accurate place recognition. Place

recognition is a key module of a SLAM system to close

loops (i.e. detect when the sensor returns to a mapped area

and correct the accumulated error in exploration) and to

relocalize the camera after a tracking failure, due to occlusion

or aggressive motion, or at system re-initialization. Therefore

Visual SLAM, where the main sensor is a camera, has been

strongly developed in the last years.

Visual SLAM can be performed by using just a monocular

camera, which is the cheapest and smallest sensor setup.

However as depth is not observable from just one camera,

the scale of the map and estimated trajectory is unknown.

In addition the system bootstrapping require multi-view or

ﬁltering techniques to produce an initial map as it cannot

be triangulated from the very ﬁrst frame. Last but not least,

monocular SLAM suffers from scale drift and may fail if

performing pure rotations in exploration. By using a stereo

or an RGB-D camera all these issues are solved and allows

for the most reliable Visual SLAM solutions.

In this paper we built on our monocular ORB-SLAM [1]

and propose ORB-SLAM2 with the following contributions:

(a) Stereo input: trajectory and sparse reconstruction of an urban environ-

ment with multiple loop closures.

(b) RGB-D input: keyframes and dense pointcloud of a room scene with

one loop closure. The pointcloud is rendered by backprojecting the sensor

depth maps from estimated keyframe poses. No fusion is performed.

Fig. 1. ORB-SLAM2 processes stereo and RGB-D inputs to estimate

camera trajectory and build a map of the environment. The system is able

to close loops, relocalize, and reuse its map in real-time in standard CPUs

with high accuracy and robustness.

• The ﬁrst open-source

SLAM system for monocular,

stereo and RGB-D cameras, including loop closing,

relocalization and map reuse.

• Our RGB-D results shows that by using Bundle Ad-

justment (BA) we achieve more accuracy than state-of-

the-art methods based on ICP or photometric and depth

error minimization.

arXiv:1610.06475v1 [cs.RO] 20 Oct 2016

下载后可阅读完整内容，剩余6页未读，立即下载

happzhao

粉丝: 23
资源: 7

ORB-SLAM2：多模态SLAM系统实现实时定位与建图

ORB-SLAM2源码解析与系统总结

ORB-SLAM2：开源视觉SLAM系统详解

ORB-SLAM2：实时准确的单目视觉SLAM系统

_home_yrl_ORB_SLAM2_CMakeLists.txt.pdf

orb_slam_detailed_explanation-master.zip

ORB_SLAM3官方标定文档的中文版

基于点线综合特征的双目视觉SLAM方法.pdf_vslam_slam_双目slam_

ORB-SLAM_ a Versatile and Accurate Monocular SLAM System.pdf

视觉slam.pdf.zip

ORB-SLAM2详解.pdf

最新资源