輪型機器人之影像對正與實作

Toward the implementation of image registration of a mobile-robot

吳吉翔(Gi-Shiang Wu)

指導教授 ： 陳建祥

國立清華大學/工學院/動力機械工程學系/碩士(2009年)

https://doi.org/10.6843/NTHU.2009.00539

摘要

本文以嵌入式系統(EBC 320 Embedded System)為平台，以攝影機擷取2D影像，並利用NI控制卡控制伺服馬達搭配雷射尋標器(Laser Range Finder)對環境掃描來重構視覺影像。利用此兩不同設備，將視覺影像與攝影機所擷取的影像進行影像對正(image registration)。
影像對正主要分為『手動影像對正』與『自動影像對正』，首先是利用MATLAB程式語言將攝影機所擷取的影像圖片和雷射尋標器所掃描的視覺影像進行手動影像對正並做小波影像融合，目的是驗證影像對正是否可行，接著，在視窗程式開發環境下，進行自動化對正探討。利用了自動化影像對正的方法和定義視區範圍來當作輪型機器人閃避障礙物的依據。因此，實作輪型機器人穿越不同狹縫寬度障礙物與不同高度障礙物之測試。

關鍵字

影像對正 ； 雷射 ； 輪型機器人

並列摘要

In this thesis, an embedded system (EBC 320 Embedded System) as a platform to capture 2D camera image, and take advantage of NI control card to control servo motor with a laser range finder to scan the environment for reconstruction of visual image. Using the two different devices, visual images and images captured by camera for image registration.

The image registration is carried out with manual and automated image registration. The first is the use of MATLAB programming language, with image captured by camera and visual image scanned by laser range finder to carry out image registration manually and image fusion with wavelet transformation, the purpose is to verify the feasibility of image registration, and then, in the window program development environment for automated image registration to explore. On the basis of use of automated image registration and definitions as the visual area for wheel-robot is to avoid obstacles. These are tests for wheel-robot through obstacles in different width of slit and different heights to further validate its efficiency.

並列關鍵字

image registration ； laser range finder ； wheeled-robot

參考文獻

[3] Ardeshir Goshtasby, “Image registration by local approximation methods”, Image Vision Computing. 6, pp. 255–261, 1988.

[6] NEXCOM, Embedded Board Computer EBC 320 Series User’s Manual Version 1.1,August ,2007.

[9] Q. Zheng, R. Chellapa, “A computational vision approach to image

[10] A. Noble, “Finding corners,” Image and Vision Computing 6, pp 121–128, 1988.

[11] W.K. Pratt, Digital Image Processing, 2nd ed., Wiley, New York,