您现在的位置:网站首页答辩论文工学论文土建水利学

图象处理及其在机器人障碍识别中的应用

  • 简介:摘 要 视觉信号具有信号探测范围宽、获取信息丰富等优点。随着近几年图像处理技术以及计算机处理能力的飞速发展,视觉导航成为机器人导航的主要发展方向之一。最近二十年来,基于视觉的室内机器人导航和室外机器人导航均得到了飞速发展。机器人导航的任...
    • 请与管理员联系购买资料 QQ:5739126
  • 论文简介
  • 相关论文
  • 论文下载

  

视觉信号具有信号探测范围宽、获取信息丰富等优点。随着近几年图像处理技术以及计算机处理能力的飞速发展,视觉导航成为机器人导航的主要发展方向之一。最近二十年来,基于视觉的室内机器人导航和室外机器人导航均得到了飞速发展。机器人导航的任务之一就是避开障碍物。这样,机器人在行走过程中,要充分利用环境中的特征来识别航行区域和障碍物区域。

本文结合国家自然科学基金和湖北省青年杰出人才基金项目的需求,提出了基于地面特征识别的室内机器人视觉导航这一课题。通过对图像处理的基本理论的研究和实践,特别是对彩色图像分割进行比较深入的学习和探讨,在已有研究的基础上,提出了一种通过分析机器人环境图像中的颜色信息来识别机器人的可行走区域和非可行走区域的方法,开发了一个机器人的实时障碍物检测系统,包括环境视频图像的采集、处理、压缩、存储和实时回放。

通过本课题的研究,得到如下的成果与结论:

(1) 详细分析了室内环境中地面的角点、边缘、颜色等特征,并且对这些特征的提取方法进行了比较,最终选取颜色特征作为机器人视觉导航的陆标;

(2) 在已有图像分割算法的基础上,对彩色图像分割算法进行了一些研究,提出了一种基于图像直方图统计学、适合于室内移动机器人识别可行走区域和障碍物区域的彩色图像分割方法;

(3) 基于DirectShow技术,完成了机器人单目视觉系统的视频图像采集、视频中每一帧图像处理、视频压缩、存储和实时回放,其中视频压缩可以选用多种压缩方式。

本文在Visual C++集成开发环境中基于OpenCVDirectShow视频采集技术编程实现了系统的功能。试验结果说明本文系统能够实时检测机器人室内环境中的障碍物,完成了视觉导航的中的避障任务。

 

关键词:室内移动机器人,视觉导航,障碍物检测,彩色图像分割

 

 

Abstract

Vision has the advantage of broad sensing area and full information. With the development of image processing technology and the ability of computer, the visual navigation is becoming a main way in robot navigation. The progress made in the last two decades has been on vision-based navigation both for indoor robots and for outdoor robots. One task of the robot navigation is avoiding obstacles. Hence, robots should recognize the drivable and the obstacle areas as they move.

With the support of project of National Scientific Fund and project of Excellent Scientist Fund in Hubei, the research on floor segmentation for indoor mobile robot visual navigation is put forward. This paper studies image processing theory, especially the color image segmentation. It puts forward a method of segmenting the scene into drivable and non-drivable areas through analyzing the color information of the input environment images and implements a system of obstacle detection, including the capture, processing, compression, saving and rendering of video images.

Through the study of this subject, some results and conclusions are drawn:

(1) This paper analyzes the features of corners, borders and color of indoor floor in detail. It also compares the methods of extraction these features. Finally the color feature is chosen as the landmark for visual navigation.

(2) This paper does research on color image segmentation based on existing image segmentation algorithms. It puts forward a color image segmentation algorithm based on histogram to segment the indoor scene into drivable and non-drivable areas.

(3) This paper implements a real-time system of video capture, processing, compression, saving and rendering based on DirectShow. The processed video images can be compressed by many methods.

Visual C++ environment, OpenCV and DirectShow tools are used. The results show that this system can implement real-time obstacle detection and avoidance.

 

Key words: indoor mobile robot, visual navigation, obstacles detection, color image segmentation

 

目录

1 绪论... 1

1.1 课题研究及意义... 1

1.2 国内外现状及发展趋势... 2

1.3 本文内容与结构... 5

1.4 本章小结... 6

2 机器人的视觉导航系统... 7

2.1 机器人的导航技术... 8

2.1.1 智能型机器人的各种导航方式... 8

2.1.2 智能机器人导航中的传感器... 9

2.2 机器人视觉导航的发展... 11

2.3 机器人视觉系统... 14

2.3.1 机器人视觉系统组成... 14

2.3.2 机器人视觉系统工作过程... 16

2.4 本章小结... 17

3 机器人视觉导航中的图像处理技术... 18

3.1 图像采集和预处... 18

3.1.1 图像的采集... 18

3.1.2 图像预处理... 19

3.2 图像分割... 22

3.2.1 边缘检测... 23

3.2.2 灰度阈值法... 26

3.2.3 颜色分割... 28

3.3 图像压缩存储... 29

3.4 本章小结... 30

4 室内地面分割的图像处理算法... 31

4.1 室内地面特征的选取... 32

4.2 图像的颜色空间的选取... 37

4.2.1 图像的颜色模型... 37

4.2.2 颜色模型变换的算法... 39

4.3 基于直方图的地面分割... 42

4.3.1 彩色图像的分割... 42

4.3.2 图像直方图的计... 47

4.3.3 直方图的反向投影... 48

4.4 本章小结... 51

5 室内机器人实时障碍物检测系统... 52

5.1 开发工具的选择... 52

5.1.1 DirectShow技术... 52

5.1.2 OpenCV视觉函数库... 54

5.2 系统实现的功能... 55

5.3 系统运行界面... 56

5.4 室内机器人障碍物检测实例... 58

5.5 本章小结... 60

6 全文总结与展望... 61

6.1 工作总结... 61

6.2 工作展望... 62

参考文献... 63

   ... 67

 

参考文献

[1] 卢韶芳,刘大维. 自主式移动机器人导航研究现状及其相关技术. 农业机械学报,200233(2)112~116.

[2] 欧青立,何克忠. 室外智能移动机器人的发展及其关键技术研究. 机器人,200022(6)519~525.

[3] Urban Bergquist. Colour Vision and Hue for Autonomous Vehicle Guidance: [Master’s Thesis paper]. Linköping: Linköping, 1999.

[4] Iwan Ulrich, Illah Nourbakhsh. Appearance-Based Obstacle Detection with Monocular Color Vision. Proc. of the AAAI. National Conference on Artificial Intelligence, Austin, TX, July/August, 2000.

[5] Parag H. Batavia, Sanjiv Singh. Obstacle Detection Using Adaptive Color Segmentation and Color Stereo Homography. Robotics and Automation, 2001. Proceedings 2001 ICRA. IEEE International Conference on Volume 1,  2001 Page(s):705 - 710.

[6] Boley D L, Sutherland K T. A rapidly converging recursive method for mobile robot localization. International Journal of Robotics Research, 1998, 17(10)1027-1039

[7] Ohya A, Kosala A, Kak. Vision-based navigation by a mobile robot with obstacle using-camera vision and ultrasonic sensing. IEEE Transactions on Robotics and Automation, 1998, 14(6)969-978

[8] Fermuller C, Cheong L F, Aloimonos Y. 3D motion and shape representationson visual servo control. International Journal of Robotics Research, 1998, 17(1)4-18

[9] Corke P I, Good M.C. Dynamic effects in visual closed-loop systems. IEEE Transactions on Robotics and Automation, 1996, 12(5)671-683

[10] Tranhanias P. Visual Recognition of Workspace Landmarks for Topological Navigation. Autonomous Robotics, 1999, 7(2): pp.143-158

[11] Stanley K, Wu Q M J. Neural Network-Based Vision Guided Robotics. Proceedings of the 1999 IEEE Inter Confon Robotics and Automation. 1999, 1: pp.281-286

[12] ToriiT, Kitade S, TeshimaT. Crop row tracking by an autonomous vehicle using machine vision(part 1). Journal of the Japanese Society of Agricultural Machinery, 2000, 62(2): pp.41-48

[13] Asada M, Kitano H. The Robocup Challenge. Robotics and Autonomous Systems 1999, 29(1): pp.3-12

[14] Simmons R, Fernandez J L, etal. Lessons learned from Xavier. IEEE Robotics & Automation Magazine, 2000: 33-39

[15] 张朋飞,何克忠,欧阳正柱等. 多功能室外智能移动机器人试验平台-THMR-V. 机器人,200224(2)97-101

[16] 方建军,何广平. 智能机器人. 北京:化学工业出版社. 2004253~87

[17] 冯建农,柳明,吴捷. 自主移动机器人智能导航研究发展. 机器人,199719(6)468-473

[18] Guilherme N.DeSouza and Avinash C. Kak. Vision for Mobile Robot NavigationA Survey. Pattern Analysis and Machine IntelligenceIEEE Transactions on Volume 24Issue 2Feb. 2002 Page(s)237 – 267

[19] Young-geun Kim, Hakil Kim. Layered Ground Floor Detection for Vision-based Mobile Robot Navigation. Proceedings of the 2004 IEEE International Coference on Robotics & Automation New Orleans, LA, April, 200413-18

[20] 阮秋琦,阮宇智等译,数字图像处理(第二版),北京:电子工业出版社,20033. Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing, Second Edition, BeijingPublishing House of Electronics Industry, 2003.

[21] 章毓普. 图像处理和分析,北京:清华大学出版社,19993.

[22] 孙即祥,图像处理,北京:科学出版社,20049

[23] 章毓普. 图像处理和分析基础,北京:高等教育出版社,20027.

[24] 方建军,何广平. 智能机器人,北京:化学工业出版社,20042.

[25] 王庆有. 图像传感器应用技术,北京:电子工业出版社,20039.

[26] 陈玥,蔡自兴. 基于DirectShow技术的移动机器人视频采集系统.华中科技大学学报(自然科学版)20043287~89.

[27] 章毓普. 图像分割,北京:科学出版社,20012.

[28] 朱志刚,林学言,石定机等译,Kenneth. R. Castleman著。数字图像处理,北京:电子工业出版社,19989.

[29] J.Canny. A Computational Approach to Edge Detection. IEEE Trans.PAMI-8.1986. Vol.PAMI-8.No.6.Nov.pp.679698.

[30] 黄贤武,王加俊等,数字图像处理与压缩编码技术,四川:电子科技大学出版社,200012.

[31] I.Horswill. Visual Collision Avoidance by Segmentation. Intelligent Robots and Systems, IROS, 1994, pp902-909.

[32] 陆新华,帐桂林. 室内服务机器人导航方法研究. 机器人,200325(1)80~87.

[33] 张尧,陈卫东. 一个基于全景视觉的移动机器人导航系统的设计与实现. 机器人,200527(2):173177182.

[34] 尚文,马旭东,戴先中,王栋耀. 基于视觉的移动机器人地面轨线跟踪导航研究. 机器人,2003 25(5)432~437.

[35] 张海波,原魁,周庆瑞. 基于路径识别的移动机器人视觉导航. 中国图象图形学报,2004 9(7)853~857.

[36] 谭晓军,郭志豪. 基于视觉的机器人导航算法研究. 中山大学学报(自然科学版)200443127~131.

[37] 李桂芝,安成万,杨国胜,谭民,涂序彦. 基于场景识别的移动机器人定位方法研究. 机器人,200527(2)123~127.

[38] 章小兵,宋爱国. 地面移动机器人研究现状及发展趋势. 机器人技术与应用,2005219~23.

[39] 杜娟,李文锋. 基于地面特征识别的室内机器人视觉导航系统的研究. 中国科技论文在线,200511-155.

[40] Volker Graefe, Karlheinz Fleder. A Powerful and Flexible Co-Processor for Feature Extraction in a Robot Vision System. Industrial Electronics, Control and Instrumentation, 1991. Proceedings. IECON 1991 International Conference on 28 Oct-1 Nov, 1991 Page: 2019~2024.

[41] Kobus Barnard, Vlad Cardei, Brian Funt. A Comparison of Computational Color Constancy AlgorithmsPart: Methodology and Experiments With Synthesized Data. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2002, VOL.11, NO.9: 972~983.

[42] Kobus Barnard, Lindsay Martin, Adam Coath, Brian Funt. A Comparison of Computational Color Constancy AlgorithmsPart: Methodology and Experiments With Synthesized Data. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2002, VOL.11, NO.9: 985~996.

[43] 张振武,丁冬花. THMR-V道路检测算法设计. 微计算机信息,200521(12-2)115~117.

[44] 杨其宇,王敏,黄振宇. 基于彩色图像的移动机器人视觉导航系统. 华中科技大学学报(自然科学版)20043283~86.

[45] 席志红,原新,许辉. 基于视觉的移动机器人实时避障和导航. 哈尔滨工程大学学报,200223(5)107~109106.

[46] 李欣,李宏东,顾伟康,李庆中. 一种结构化道路环境中的视觉导航系统. 浙江大学学报(工学版)200236(6)630633.

[47] 董士崇,王天珍,许刚. 视频图像中的运动检测. 武汉理工大学学报(信息与管理工程版)200426(4)1~317.

[48] 吕学刚,于明,刘翠响. IPLOpenCVVC++环境下的应用. 微型电脑应用,200319(1)333451.

[49] Liana M. Lorigo, Rodney A. Brooks, W. Eric L. Grimson. Visually-guided obstacle avoidance in unstructured environments. Intelliqent Robots and Systems, 1997. IROS’97, Proceedings of the 1997 IEEE/RSJ International Conference on Vol.1: 373~379.

[50] Gary Bradski, Adrian Kaehler, Vadim Pisarevsky. Learning-Based Computer Vision with Intel’s Open Source Computer Vision Library. Intel Technology Journal, 9(2): 119~130.

[51] 林开颜,吴军辉,徐立鸿. 彩色图像分割方法综述. 中国图象图形学报,2005101):1~10.

[52] 黄飞,吴敏渊,曹开田. 基于HIS空间的彩色图像分割. 小型微型计算机系统,2004253):471474.

[53] 安成万,张永谦,李桂芝,谭民. 基于分量直方图的移动机器人视觉图像自适应分割. 机器人,200426(6)254~258.

[54] 杜娟,李文锋. 基于金字塔连接算法的彩色图像分割. 武汉理工大学学报,200628(1)112~114122.

[55] P BurtT H Hong, A Rosenfeld. Segmentation and estimation of image region properties through cooperative hierarchial computation. IEEE Transactions on SystemsMan and CyberneticsDecember 198111(12):802~809.

[56] B Jahne. Digital Image Processing. SpringerNew York1997.

[57] T.Taylor, S.Geva, W.W.Boles. Monocular Vision as a Range Sensor. CIMCA 2004 Processing/ISBN: 1740881885 M. Mohannadian(Ed.)12_14 July 2004, Gold Coast-Australia: 566~575.

[58] John G. Allen, Richard Y. D. Xu, Jesse S. Jin, “Object Tracking Using CamShift Algorithm and Multiple Quantized Feature Spaces,” Proc. Pan-Sydney Area Workshop on Visual Information Processing (VIP2003), 2003, pp: 3-7.

[59] 汪海明,李平,韩波. UAV中图像处理系统的研究. 计算机工程,200531(3):178~179,191.

[60] http://www.sourceforge.net/projects/opencvlibrary

[61] http://groups.yahoo.com/group/OpenCV/

[62] http://www.assuredigit.com/forum/display_forum_topics.asp?ForumID=11

[63] http://blog.csdn.net/hunnish

 

 

查看评论 已有0位网友发表了看法
  • 验证码: