没有合适的资源?快使用搜索试试~ 我知道了~
基于单目相机与RGB-D相机的SLAM研究与设计1
需积分: 0 2 下载量 123 浏览量
2022-08-03
22:09:40
上传
评论
收藏 1.68MB PDF 举报
温馨提示
试读
79页
摘要SLAM(Simultaneous Localization And Mapping),即即时定位与地图构建技术是全自主机器人、无人驾驶、自主无人机、AR
资源详情
资源评论
资源推荐
分类号:TP242.6 密级:
学校代码:11065 学号:2015020309
硕 士 学 位 论 文
基于单目相机与 RGB-D 相机的 SLAM 研究与设计
Research And Design on SLAM Based on
Monocular And RGB-D Camera
安帅
指 导 教 师
杨杰 副教授
学 科 专 业 名 称
机械工程
培 养 单 位
机电工程学院
论 文 答 辩 日 期 2018
年
5
月
20
日
答 辩 委 员 会 主 席
赵永瑞
摘要
SLAM(Simultaneous Localization And Mapping)
,即即时定位与地图构建技术是
全自主机器人、无人驾驶、自主无人机、AR 等领域的关键技术,常用的 SLAM 传
感器有激光雷达、单目、双目、
RGB-D
等传感器。单目相机由于其价格低廉、便于
携带、信息丰富、易于与其他信息融合等优点,因此,单目 SLAM 是视觉 SLAM
研究领域中的热点也是难点。此外,
RGB-D
相机在室内比较稳定并且能够构建出稠
密地图,在室内 RGB-D SLAM 有一定的研究价值。在实际应用中,例如通常无人
机的飞行通过
GPS
进行定位,其定位精度较差且在室内、隧道、洞穴、山谷等场景
下会失效,且一般通过人工控制进行避障,不能够自主进行对环境的感知与避障。
为了克服上述不足,本文研究了单目
SLAM
算法,并将其运用于无人机采集的视频
序列当中,对无人机的自主飞行提供了一定的理论基础。RGB-D 相机由于其深度信
息容易获得,易于搭建
SLAM
矿建,本文利用
RGB-D
相机数据集进行了
SLAM
系
统的设计与实验,为后期系统的完善提供了大体框架,以进行开发与拓展。
完善的
SLAM
系统包括前端里程计、后端优化、建图与回环检测四个部分。文
中对 SLAM 系统的基本原理进行了较为深入地分析,从前端设计、后端优化、回环
检测与建图四个方面进行了数学原理的推导与程序的设计。
在前端设计中,单目 SLAM 利用对极几何计算了本质矩阵 E 和单应性矩阵 H,
并分解这两个矩阵,经过验证之后得到正确的位姿,然后利用该位姿进行三角测量
得到地图点的三维坐标,再利用 PnP 的方法解算后续的位姿与地图点,RGB-D 相
机的前端设计中则直接用
PnP
进行位姿估计与地图点的求解,在基于直接法的前端
设计中,则是利用最小化光度误差(Photometric Error)进行迭代求解位姿与地图点;
进行后端优化时,利用
Ceres
库与
G2O
库通过高斯牛顿、列文伯格——马库尔特等
算法来进行迭代优化,得到优化后的相机位姿与地图点;建图部分则分别利用
ORB-SLAM2
、
LSD-SLAM
和
RGB-D
数据建立稀疏地图、稠密地图与占据栅格地
图,根据地图形式可达到进行定位、导航与避障等功能;回环检测中利用基于机器
学习中非监督学习的方法来检测已出现的图像,并构造了基于
ORB
特征训练的字
典,然后进行了词带模型的建立并利用 TF-IDF 权值构造方法计算了图像的相似性,
以进行正确的回环检测。
关键词:单目 SLAM;RGB-D SLAM;非线性优化;地图构建;三维重建
Abstract
Simultaneous Localization And Mapping (SLAM) technology is the key technology in the
field of autonomous robot, autonomous driving, autonomous UAV and AR. The most frequently
used SLAM sensors include lidar, monocular camera, stereo camera, RGB-D camera and so on.
It is regared as a hot and difficult issue because of the advantage of the low cost, portability, rich
information, easily integration with other sensor information and so on in the field of visual
SLAM. In addition, the RGB-D camera is more stable indoors than outdoors and can build a
dense map through the tcechnology of SLAM. Therefore, indoor SLAM is also worth
investigating. In practical applications, for example, the fly of UAV is generally localized by the
GPS, but the localization accuracy is low and it would lead to invalidation in the scene of the
indoors , tunnnel, cave, vally etc.To overcome the faults above, the monocular SLAM algorithm
has been researched in this thesis, and it was applied to the video sequences collected by the DJI
UAV which offers theoretical bases for the autonomous flight of the UAVs.
A perfect SLAM system includes front-end design, back-end optimization, map building
andloopdetection. In this thesis, basic principles of SLAM system are deeply analyzed and
mathematical principles are deduced and the program has been designed from these four aspects.
1. In the front-end design, the essential matrix E and the homography matrix H had been
calculated exploiting the epipolar geometry for the monocular SLAM, and these two matrices
had been decomposed to get the correct pose after verification, then 3D map points were solved
out by triangulation exploiting this pose, the subsequent poses and map point would be estimated
through Perspective-n-Point(PnP); While the pose and map point estimation of the RGB-D
camera front-end was directly calculated through PnP algorithm; However, in the front-end
design based on the direct method, the pose and the map point are iteratively solved by
minimizing the Photometric Error. In this thesis, feature extraction and matching, pose estimation
and triangulation and the other principles has been analyzed through the monocular UAV pictures,
then the front-end system has been constructed based on RGB-D dataset, and it works and can be
improvec and expanded in the future.
2. In the back-end optimization, Levenberg-Marquardt algorithm and other algorithms has
been used for iterative optimization by exploiting Ceres library and G2O library, so the camera
pose estimation and the map point has been optimized, we found that Ceres library worked faster
in the dataset we had choosed.
3. In the part of map building, the sparse map, dense map and occupancy grid map were
built with the ORB-SLAM2, LSD-SLAM and RGB-D dataset respectively, functions of
localization, navigation, and obstacle avoidance could be realized according to different map
types, and the occupancy grid map has the advantage of small size memory occupation.
4. In the looping detection, emerged pictures were detected by unsupervised learning
algorithm based on machine learning, and the dictionary based on ORB feature training was
constructed, then bag of words model was constructed and the picture similarity was calculated
by TF-IDF weights construction algorithm and the correct loop was detected.
Key Words:Monocular SLAM;RGB-D SLAM;Nonlinear Optimization;Mapping;
3-D Reconstruction
剩余78页未读,继续阅读
赵伊辰
- 粉丝: 56
- 资源: 314
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0