ORB-SLAM2：实时准确的单目视觉SLAM系统

需积分: 46 200 浏览量更新于2024-07-17 2 收藏 1.78MB PDF 举报

"ORB-SLAM2的PDF论文，关于视觉SLAM的研究，涵盖了实时、室内外环境下的单目SLAM系统设计与实现" 在计算机视觉领域，SLAM（Simultaneous Localization And Mapping，同时定位与建图）是一项关键技术，用于使机器人或设备在未知环境中自主导航并构建环境地图。ORB-SLAM是这一领域的里程碑式工作，尤其是其第二代版本ORB-SLAM2，由Raul Mur-Artal、J.M.M. Montiel和Juan D. Tardós等人提出，详尽地阐述了一个功能强大且精确的单目SLAM系统。这篇发表在IEEETRANSACTIONSONROBOTICS 2015年的论文介绍了ORB-SLAM2的核心特性。该系统具备实时处理能力，无论是在小型室内场景还是大型室外环境中，都能稳定运行。ORB-SLAM2的创新之处在于其对特征的统一使用，它使用ORB（Oriented FAST and Rotated BRIEF）特征进行跟踪、建图、重定位和闭环检测等所有SLAM任务，极大地提高了系统的效率和鲁棒性。系统的关键特性包括： 1. **鲁棒性**：ORB-SLAM2能有效应对复杂的运动噪声，即使在动态环境下也能保持稳定。 2. **宽基线闭环检测**：允许在大视角变化下完成闭环，这对于保持地图一致性至关重要。 3. **自动初始化**：系统具备自动初始化功能，无需人工干预即可开始SLAM过程。 4. **生存优胜策略**：通过一种“适者生存”的策略，选择重建中的关键点和关键帧，确保地图的紧凑性和可追踪性。这使得地图仅在场景内容发生变化时增长，适应长期操作需求。 5. **全面评估**：ORB-SLAM2在多个公开数据集上的27个序列进行了详尽的性能测试，对比其他最先进的方法，表现出前所未有的优秀性能。 ORB-SLAM2的出现，推动了SLAM技术的发展，其在实时性、准确性和鲁棒性方面的突出表现，使其成为学术界和工业界研究和应用的首选方案。这篇论文不仅提供了深入的技术细节，也对后来的SLAM研究和实际应用产生了深远影响。

1150 IEEE TRANSACTIONS ON ROBOTICS, VOL. 31, NO. 5, OCTOBER 2015

Fig. 1. ORB-SLAM system overview, showing all the steps performed by the

tracking, local mapping, and loop closing threads. The main components of the

place recognition module and the map are also shown.

searched by reprojection, and camera pose is optimized again

with all matches. Finally, the tracking thread decides if a new

keyframe is inserted. All the tracking steps are explained in de-

tail in Section V. The novel procedure to create an initial map

is presented in Section IV.

The local mapping processes new keyframes and performs lo-

cal BA to achieve an optimal reconstruction in the surroundings

of the camera pose. New correspondences for unmatched ORB

in the new keyframe are searched in connected keyframes in

the covisibility graph to triangulate new points. Some time after

creation, based on the information gathered during the track-

ing, an exigent point culling policy is applied in order to retain

only high quality points. The local mapping is also in charge

of culling redundant keyframes. We explain in detail all local

mapping steps in Section VI.

The loop closing searches for loops with every new keyframe.

If a loop is detected, we compute a similarity transformation

that informs about the drift accumulated in the loop. Then, both

sides of the loop are aligned and duplicated points are fused.

Finally, a pose graph optimization over similarity constraints [6]

is performed to achieve global consistency. The main novelty is

that we perform the optimization over the Essential Graph, i.e.,

a sparser subgraph of the covisibility graph which is explained

in Section III-D. The loop detection and correction steps are

explained in detail in Section VII.

We use the Levenberg–Marquardt algorithm implemented in

g2o [37] to carry out all optimizations. In the Appendix, we

describe the error terms, cost functions, and variables involved

in each optimization.

C. Map Points, Keyframes, and Their Selection

Each map point p

stores the following:

1) its 3-D position X

w,i

in the world coordinate system;

2) the viewing direction n

, which is the mean unit vec-

tor of all its viewing directions (the rays that join

Fig. 2. Reconstruction and graphs in the sequence fr3 long

office household from the TUM RGB-D Benchmark [38]. (a) Keyframes

(blue), current camera (green), map points (black, red), current local map points

(red). (b) Covisibility graph. (c) Spanning tree (green) and loop closure (red).

(d) Essential graph.

the point with the optical center of the keyframes that

observe it);

3) a representative ORB descriptor D

, which is the asso-

ciated ORB descriptor whose hamming distance is mini-

mum with respect to all other associated descriptors in the

keyframes in which the point is observed;

4) the maximum d

max

and minimum d

min

distances at which

the point can be observed, according to the scale invari-

ance limits of the ORB features.

Each keyframe K

stores the following:

1) the camera pose T

, which is a rigid body transforma-

tion that transforms points from the world to the camera

coordinate system;

2) the camera intrinsics, including focal length and principal

point;

3) all the ORB features extracted in the frame, associated or

not with a map point, whose coordinates are undistorted

if a distortion model is provided.

Map points and keyframes are created with a generous policy,

while a later very exigent culling mechanism is in charge of

detecting redundant keyframes and wrongly matched or not

trackable map points. This permits a ﬂexible map expansion

during exploration, which boost tracking robustness under hard

conditions (e.g., rotations, fast movements), while its size is

bounded in continual revisits to the same environment, i.e.,

lifelong operation. Additionally, our maps contain very few

outliers compared with PTAM, at the expense of containing

less points. Culling procedures of map points and keyframes

are explained in Sections VI-B and VI-E, respectively.

剩余16页未读，继续阅读

无上境

粉丝: 1
资源: 1

ORB-SLAM2：实时准确的单目视觉SLAM系统

崔华坤VINS、MSCKF/ROVIO论文推导和代码解读

SLAM论文集锦

orbslam2 代码详细解读

ORB-SLAM2 论文pdf

ORB-SLAM3论文.pdf

orb_slam.pdf

ORB-SLAM2：开源视觉SLAM系统详解

ORB-SLAM2- an Open-Source SLAM System.pdf

论文研究-单目视觉SLAM算法研究 .pdf

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

最新资源