一、SLAM框架
RGB-D SLAM开源
SLAM 主要分为两个部分:前端和后端,前端也就是视觉里程计(VO),它根据相邻图像的信息粗略的估计出相机的运动,给后端提供较好的初始值。VO的实现方法可以根据是否需要提取特征分为两类:基于特征点的方法,不使用特征点的直接方法。 基于特征点的VO运行稳定,对光照、动态物体不敏感。
二、视觉里程计框架
三、视觉里程计主要研究方法
四、视觉里程计发展状况
五、SLAM大佬网站
1、跟踪SLAM前沿动态论文,更新的很频繁
https://github.com/YiChenCityU/Recent_SLAM_Research
2、很全视觉slam资料大全
https://github.com/tzutalin/awesome-visual-slam
3、开源SLAM列表
https://github.com/OpenSLAM/awesome-SLAM-list
4、很全面的SLAM教程
https://link.zhihu.com/?target=https%3A//github.com/kanster/awesome-slam
5、非常全面的三维重建相关资源列表,涵盖SLAM,SFM,MVS
https://github.com/openMVG/awesome_3DReconstruction_list
6、很全的RGBD SLAM开源方案介绍
https://github.com/electech6/owesome-RGBD-SLAM
7、非常全面的相机总结,包括论文,设备厂商,算法,应用等
https://github.com/uzh-rpg/event-based_vision_resources
8、SLAM 学习与开发经验分享
https://github.com/GeekLiB/Lee-SLAM-source
9、中文注释版ORB-SLAM2
https://github.com/Vincentqyw/ORB-SLAM2-CHINESE
10、语义SLAM相关资料
https://zhuanlan.zhihu.com/p/64825421
11、很好的博客
https://blog.csdn.net/kyjl888/category_6954673.html
六、SLAM相关的工具和库
基础工具:Eigen、OpenCV、PCL、ROS
后端优化的库:g2o、GTSAM、Ceres solver
七、SLAM相关开源代码
主要视觉里程计代码及论文
SVO: Fast Semi-Direct Monocular Visual Odometry
论文:http://rpg.ifi.uzh.ch/docs/ICRA14_Forster.pdf
代码:https://github.com/uzh-rpg/rpg_svo
Robust Odometry Estimation for RGB-D Cameras
Real-Time Visual Odometry from Dense RGB-D Images
论文:http://www.cs.nuim.ie/research/vision/data/icra2013/Whelan13icra.pdf
代码:https://github.com/tum-vision/dvo
Parallel Tracking and Mapping for Small AR Workspaces
论文:https://cse.sc.edu/~yiannisr/774/2015/ptam.pdf
http://www.robots.ox.ac.uk/ActiveVision/Papers/klein_murray_ismar2007/klein_murray_ismar2007.pdf
代码:https://github.com/Oxford-PTAM/PTAM-GPL
ORBSLAM
代码:https://github.com/raulmur/ORB_SLAM2
https://github.com/raulmur/ORB_SLAM
A ROS Implementation of the Mono-Slam Algorithm
论文:https://www.researchgate.net/publication/269200654_A_ROS_Implementation_of_the_Mono-Slam_Algorithm
代码:https://github.com/rrg-polito/mono-slam
DTAM: Dense tracking and mapping in real-time
论文:https://ieeexplore.ieee.org/document/6126513
代码:https://github.com/anuranbaka/OpenDTAM
LSD-SLAM: Large-Scale Direct Monocular SLAM
论文:http://pdfs.semanticscholar.org/c13c/b6dfd26a1b545d50d05b52c99eb87b1c82b2.pdf
https://vision.in.tum.de/research/vslam/lsdslam
代码:https://github.com/tum-vision/lsd_slam
MSCKF_VIO:Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight
论文:https://arxiv.org/abs/1712.00036
代码:https://github.com/KumarRobotics/msckf_vio
LIBVISO2: C++ Library for Visual Odometry 2
论文:http://www.cvlibs.net/software/libviso/
代码:https://github.com/srv/viso2
Stereo Visual SLAM for Mobile Robots Navigation
A constant-time SLAM back-end in the continuum between global mapping and submapping: application to visual stereo SLAM
论文:http://mapir.uma.es/famoreno/papers/thesis/FAMD_thesis.pdf
代码:https://github.com/famoreno/stereo-vo
Combining Edge Images and Depth Maps for Robust Visual Odometry
Robust Edge-based Visual Odometry using Machine-Learned Edges(REVO)
论文:https://graz.pure.elsevier.com/
代码:https://github.com/fabianschenk/REVO
HKUST Aerial Robotics Group
VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
论文:https://arxiv.org/pdf/1708.03852.pdf
代码:https://github.com/HKUST-Aerial-Robotics/VINS-Mono
VINS-Fusion:Online Temporal Calibration for Monocular Visual-Inertial Systems
论文:https://arxiv.org/pdf/1808.00692.pdf
代码;https://github.com/HKUST-Aerial-Robotics/VINS-Fusion
Monocular Visual-Inertial State Estimation for Mobile Augmented Reality
论文:https://ieeexplore.ieee.org/document/8115400
代码:https://github.com/HKUST-Aerial-Robotics/VINS-Mobile
VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem
论文:https://arxiv.org/abs/1701.08376
代码:https://github.com/HTLife/VINet
Computer Vision Group TUM Department of Informatics Technical University of Munich
DSO: Direct Sparse Odometry
代码;https://github.com/JingeTu/StereoDSO
Visual-Inertial DSO:https://vision.in.tum.de/research/vslam/vi-dso
DVSO:https://vision.in.tum.de/research/vslam/dvso
DSO with Loop-closure and Sim(3) pose graph optimization:https://vision.in.tum.de/research/vslam/ldso
Stereo odometry based on careful feature selection and tracking
论文:https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7324219
代码:https://github.com/Mayankm96/Stereo-Odometry-SOFT
OKVIS: Open Keyframe-based Visual-Inertial SLAM
代码:https://github.com/gaoxiang12/okvis
Trifo-VIO: Robust and Efficient Stereo Visual Inertial Odometry using Points and Lines
论文:https://arxiv.org/pdf/1803.02403.pdf
代码:https://github.com/UMiNS/Trifocal-tensor-VIO
PL-VIO: Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features
论文:https://www.mdpi.com/1424-8220/18/4/1159/html
A Review of Visual-Inertial Simultaneous Localization and Mapping from Filtering-Based and Optimization-Based Perspectives:视觉惯导的综述性文章
八、SLAM相关数据集
1. Malaga Dataset
2. Tum: Computer Vision Lab: RGB-D
3. KITTI Dataset
4. University of Freiburg: Department of Computer Science
5. MRPT
6. ICDL-NUIM
九、推荐阅读
如何从零开始系统化学习视觉SLAM?
从零开始一起学习SLAM | 为什么要学SLAM?
从零开始一起学习SLAM | 学习SLAM到底需要学什么?
从零开始一起学习SLAM | SLAM有什么用?
从零开始一起学习SLAM | C++新特性要不要学?
从零开始一起学习SLAM | 为什么要用齐次坐标?
从零开始一起学习SLAM | 三维空间刚体的旋转
从零开始一起学习SLAM | 为啥需要李群与李代数?
从零开始一起学习SLAM | 相机成像模型
从零开始一起学习SLAM | 不推公式,如何真正理解对极约束?
从零开始一起学习SLAM | 神奇的单应矩阵
从零开始一起学习SLAM | 你好,点云
从零开始一起学习SLAM | 给点云加个滤网
从零开始一起学习SLAM | 点云平滑法线估计
从零开始一起学习SLAM | 点云到网格的进化
从零开始一起学习SLAM | 理解图优化,一步步带你看懂g2o代码
从零开始一起学习SLAM | 掌握g2o顶点编程套路
从零开始一起学习SLAM | 掌握g2o边的代码套路
零基础小白,如何入门计算机视觉?
SLAM领域牛人、牛实验室、牛研究成果梳理
我用MATLAB撸了一个2D LiDAR SLAM
可视化理解四元数,愿你不再掉头发
最近一年语义SLAM有哪些代表性工作?
视觉SLAM技术综述
汇总 | VIO、激光SLAM相关论文分类集锦
研究SLAM,对编程的要求有多高?
2018年SLAM、三维视觉方向求职经验分享
2018年SLAM、三维视觉方向求职经验分享
深度学习遇到SLAM | 如何评价基于深度学习的DeepVO,VINet,VidLoc?
视觉SLAM关键方法总结
SLAM方向公众号、知乎、博客上有哪些大V可以关注?
SLAM实验室
SLAM方向国内有哪些优秀公司?
SLAM面试常见问题
SLAM相关领域数据集调研
从零开始一起学习SALM-ICP原理及应用
十、SLAM学习书籍
-
概率机器人
-
视觉SLAM十四讲
-
计算机视觉中的多视图几何
-
机器人学中的状态估计
-
Principles of Robot Motion Theory,Algorithms and Implementation
在公众号【3DCVer】后台回复“SLAM学习资料”,获取完整PDF资料。
十一、SLAM学习视频
公开课:
https://www.youtube.com/channel/UCi1TC2fLRvgBQNe-T4dp8Eg