CASIA OpenIR  > 毕业生  > 硕士学位论文
Alternative TitleIndoor Localization of Mobile Robot Based on Embedded Vision System and Passive Infrared Landmarks
Thesis Advisor李成荣 ; 罗杨宇
Degree Grantor中国科学院研究生院
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嵌入式视觉定位 无源红外路标 图像处理 单应矩阵 误差补偿 Embedded Vision Localization Passive Infrared Landmark Image Processing Homography Error Compensation
Abstract随着科技水平的进步和人们对生活品质的要求越来越高,室内移动机器人的应用领域越来越广泛。在自主移动机器人的研究领域中,机器人自定位是一个非常重要的研究方向,是实现机器人自动导航和其它智能行为的前提。本文针对运行在室内环境下的移动机器人的视觉定位问题开展研究,设计了一种基于嵌入式视觉系统和无源红外路标的机器人定位系统和方法,主要包括以下几个方面的内容: 第一,针对室内移动机器人视觉定位问题,设计了一种基于ARM STM32F4微控制器的嵌入式视觉定位系统。详细介绍了该系统的ARM控制器最小系统模块、红外发光模块、图像传感器以及LCD显示模块等的设计;在硬件设计基础上,实现了基于ARM DCMI接口的图像采集与显示。 第二,针对路标设计以及路标图像识别问题,实现了一种无源红外路标的设计与识别方法。设计了一种3×3型的无源矩阵方格红外路标;针对路标图像的特点,研究了适合嵌入式计算的图像处理方法,具体包括图像二值化、连通域检测以及路标识别点的聚类方法;在此基础上,研究了路标的坐标系识别以及ID识别方法。 第三,针对机器人位姿计算问题,设计了基于单应矩阵的定位方法,通过测量的路标图像坐标计算得到机器人的位姿。针对由于摄像机安装误差、机器人移动过程中的颠簸等造成的机器人定位偏差问题,分析了垂直关系假设的合理性,实现了定位误差的补偿方法。 最后,对本文的研究成果进行了总结,并指出了下一步的研究方向。
Other AbstractWith the improvement of technology and the increasing demands of life qualities, indoor mobile robot is being widely applied to our daily life. As the prerequisite to realize navigation and other intelligent actions, robot localization is one of the most important research branches of autonomous mobile robot. Considering visual localization of indoor mobile robot, a vision system for the mobile robot based on embedded system and passive infrared landmark is proposed. Contributions of this paper are summarized as follows: Firstly, in order to resolve the problem of the visual localization of indoor mobile robot, an embedded system based on ARM ST32F4 microcontroller is designed. The minimal system model, infrared model, image sensor model and the LCD display model are discussed in detail. Based on the hardware, an image grabbing and displaying method is proposed. Secondly, a kind of passive infrared dot-matrix landmark (3*3) is designed. In order to realize landmark recognition, a serial of methods suitable for embedded computation are proposed, such as the image binaryzation, connected area detection and the landmark clustering. The coordinates of the landmark and its ID recognition methods are also proposed. Thirdly, a localization method to compute the pose and position of the indoor mobile robot based on homography is presented. The translation and rotation of a certain landmarks on visual field is computed and used to estimate the pose and position of the robot. In order to compensate the localization error caused by camera installation or the shaking of the robot, a localization error compensation method is proposed.
Other Identifier200628014628062
Document Type学位论文
Recommended Citation
GB/T 7714
杨广京. 基于嵌入式平台的无源红外路标定位系统研究[D]. 中国科学院自动化研究所. 中国科学院研究生院,2012.
Files in This Item:
File Name/Size DocType Version Access License
CASIA_20062801462806(1494KB) 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[杨广京]'s Articles
Baidu academic
Similar articles in Baidu academic
[杨广京]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[杨广京]'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.