CASIA OpenIR  > 毕业生  > 博士学位论文
快速鲁棒的相机定位
Alternative TitleFast and Robust Camera Localization
冯友计
Subtype工学博士
Thesis Advisor吴毅红
2014-12-01
Degree Grantor中国科学院大学
Place of Conferral中国科学院自动化研究所
Degree Discipline模式识别与智能系统
Keyword三维重建 三维跟踪 基于图像的相机定位 二进制特征索引 同步定位与地图构建 重定位 3d Reconstruction 3d Tracking Image-based Camera Localization Binary Feature Indexing Slam Relocalization
Abstract相机定位是三维计算机视觉的一个基本问题,其任务是根据相机拍摄的图像估计相机的姿态。它也是增强现实,人机交互,视觉伺服,视觉导航等诸多应用的核心技术,一直都受到视觉界研究者们的广泛关注。相机定位的外延非常丰富,三维视觉领域很多研究分支本质上都是在处理这一问题,例如物体的三维跟踪(3D tracking)、同步定位与地图构建(simultaneous localization and mapping,SLAM)、基于图像的定位(image-based localization)等等。本文探索了三种不同场合下的相机定位,即视频中物体的三维跟踪、室外大场景中基于图像的定位、较大场景中SLAM的重定位,针对定位的易用性、鲁棒性和速度等问题进行了研究。主要贡献如下: 构建了一个采用普通单目摄像头进行物体在线三维重建与实时三维跟踪的系统。和现有的物体三维跟踪系统不同,该系统不需要用户离线的建立三维模型,可以在简单的初始化交互之后自动的对目标物体进行重建与跟踪,使用更加灵活方便。传统的SLAM技术能对图像中的整个静止场景进行在线重建,却无法处理场景中某个特定的或运动或静止的物体。该系统对它进行了扩展,其基本思想是将SLAM与图像分割进行结合:一方面利用分割将目标物体从图像中提取出来,让重建不受背景的影响而只在物体的区域上进行;另一方面在对图像进行分割时,利用已有的重建和跟踪结果来为分割提供一些位置先验从而提高分割的精度。系统中还采用了一系列的策略来提高跟踪的稳定性和整个系统的鲁棒性。 提出了一种采用二进制特征的大场景中的相机快速定位方法。首先使用二进制特征替代现有方法中常用的SIFT特征,大大减少了特征提取的时间,然后通过对二进制特征进行有监督的索引来达到高效的近似最近邻搜索,从而为定位提供快速的二维-三维匹配。索引采用随机树的结构并利用数据库中的标签信息对随机树的节点测试进行学习,以使得落在随机树各叶节点中的数据库特征数量尽量一致并且相互匹配(具有相同标签)的特征尽量落在相同的叶节点。最后还提出了一种基于概率的优先搜索策略,通过优先搜索真实匹配最有可能落在的叶节点来进一步提高搜索的效率。在几个大场景数据集(包含数百万三维点和上千万特征)上的实验结果表明,采用提出的索引方法进行近似最近邻搜索的效率要显著高于现有的二进制特征索引方法。 而整个基于二进制特征的定位方法与传统的采用SIFT特征的定位方法相比,在速度提高了接近一个数量级的同时又保持了相当的定位成功率和定位精度。 提出了一种在线学习的二进制特征索引方法并将其应用到了较大场景下的实时的SLAM重定位当中。和流行的局部性敏感哈希(locality sensitive hashing,LSH)不同,该方法中的哈希键是通过在线学习而不是纯粹的随机选择得来的。学习过程以获得大小更均匀的哈希桶和更高的哈希碰撞率为目的来构建哈希键。这使得该方法能够获得比LSH更高的近似最近邻搜索的效率。通过将在线学习的操作分散在SLAM的过程中,该方法被成功的应用到实时的SLAM重定位中。实验表明采用该方法的重定位模块能在地图中包含数万个三维点、数十万个特征的情况下实...
Other AbstractCamera localization is a fundamental problem in 3D computer vision, referring to estimating the camera pose of an image. As is crucial in applications such as augmented reality, human-computer interaction, visual servo, and robot navigation,it has been extensively studied in the community. Many topics such as 3D tracking of objects, simultaneous localization and mapping(SLAM), image-based localization are addressing the problem in essence. This dissertation investigates camera localization in three different scenarios, i.e. 3D tracking of an object, image-based localization in large scale environments, SLAM relocalization,and focuses on the problems of ease of use, robustness and speed. The main contributions are as follows. An online object reconstruction and 3D tracking system which uses a single webcam is proposed.Unlike the prevalent 3D tracking systems based on prior models,it does not require the users to build 3D models off line. Instead, it automatically reconstructs and tracks the target object after some simple interactions, and hence is more flexible and easier to use.While traditional SLAM techniques are able to reconstruct static scenes online, they can not be used directly for online reconstruction of an object which might be moving.The system goes beyond this and the basic idea is to combine image segmentation and SLAM techniques.On the one hand, image segmentation prevents backgrounds from contaminating the reconstruction process.On the other hand, results of the reconstruction and tracking provide a location priori to improve the accuracy of segmentation.The system also employs some strategies to improve the robustness and stability. An approach for fast localization in large scale environments is proposed.First binary feature instead of real value features like SIFT, which is employed by most existing localization approaches,are used to dramatically reduce the time cost of feature extraction. Besides, a supervised indexing method is proposed to achieve highly efficient approximate nearest neighbor search, which brings about fast 2D-3D matching for localization. The indexing method resorts to randomized trees and uses label information contained in localization databases to train the structures of randomized trees. Specifically, the node tests of the trees are selected to make the numbers of database features in each leaf node as uniform as possible, and matched features collide in the same leaf nodes as much as possible. To...
Other Identifier201018014628035
Language中文
Document Type学位论文
Identifierhttp://ir.ia.ac.cn/handle/173211/6664
Collection毕业生_博士学位论文
Recommended Citation
GB/T 7714
冯友计. 快速鲁棒的相机定位[D]. 中国科学院自动化研究所. 中国科学院大学,2014.
Files in This Item:
File Name/Size DocType Version Access License
CASIA_20101801462803(11090KB) 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[冯友计]'s Articles
Baidu academic
Similar articles in Baidu academic
[冯友计]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[冯友计]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.