立體影像量測系統應用於立體氣壓三軸平行機械臂之研究

Development of a Stereo Vision Measurement System for a 3D Three Axial Pneumatic Parallel Mechanism Robot Arm

侯建綸(Chien-Lun Hou)

指導教授 ： 江茂雄

國立臺灣大學/工學院/工程科學及海洋工程學研究所/碩士(2010年)

https://doi.org/10.6342/NTU.2010.03303

摘要

本文旨在發展立體視覺三維位置測量系統應用於氣壓三軸平行機械臂，以本研究發展之立體視覺三維位置測量系統量測氣壓三軸平行機械臂之運動平台端點(End Effector)之三維空間軌跡。
為了追踪氣壓三軸平行機械臂之運動平台端點，本研究利用圓偵測演算法偵測得運動平台端點上之目標，爾後利用SAD演算法持續跟踪移動目標，並於相應之立體影像中沿其共軛極線上(Epipolar line)搜尋相應之目標位置。立體雙CCD攝影機組經校正後，藉由求得之個別攝影機內部參數和立體攝影機組之外部參數，來修正影像之扭曲，並利用立體影像對之極線校正(Epipolar rectification)方法，使立體匹配(Stereo matching)之搜索範圍縮減至沿一維之水平共軛極線。最後，運動平台端點之三維空間座標可由立體三角(Stereo triangulation)計算求得。
由實驗結果證實，本研究發展之立體視覺三維位置測量系統可成功地應用於量測立體氣壓三軸平行機械臂之運動平台端點之空間軌跡，分別為五階軌跡、正弦軌跡、三維直線軌跡和三維圓軌跡。

關鍵字

立體視覺 ； 立體重建 ； 被動式感測 ； 圓偵測 ； 影像校正 ； 平行機構機械臂

並列摘要

In this thesis, a stereo vision 3D position measurement system for the three-axial pneumatic parallel mechanism robot arm is presented. The stereo vision 3D position measurement system aims to measure the 3D trajectories of the end-effector of the three-axial pneumatic parallel mechanism robot arm.
In order to track the end-effector of the robot arm, the circle detection algorithm is used to detect the desire target and the SAD algorithm is used to track moving target and to search the corresponding target location along the conjugate epipolar line in the stereo pair. After camera calibration, both intrinsic and extrinsic parameters of the stereo rig can be obtained so that images can be rectified according to camera parameters, and through the use of the epipolar rectification, the stereo matching process is reduced to a horizontal search along the conjugate epipolar line. Finally, 3D trajectories of the end-effector are computed by stereo triangulation.
The experiment results show that the stereo vision 3D position measurement system proposed in this thesis can successfully track and measure the fifth-order polynomial trajectory, sinusoidal trajectory, 3D straight-line trajectory, and 3D circle trajectory of the end-effector of the three axial pneumatic parallel mechanism robot arm.

並列關鍵字

stereo vision ； 3D reconstruction ； passive perception ； circle detection ； image rectification ； parallel mechanism robot arm

參考文獻

[1] Arturo L. Rankin, Andres Huertas, and Larry H. Matthies, “Stereo vision based terrain mapping for off-road autonomous navigation,” Proc. SPIE, Vol. 7332, pp. 733210-733210-17, 2009.

[3] Rogerio Richa, Philippe Poignet and Chao Liu, “Three-dimensional Motion Tracking for Beating Heart Surgery Using a Thin-plate Spline Deformable Model,” Int. J. of Robotic Research, Vol. 29, No. 2-3, pp. 218-230, 2010.

[6] A. Peleg and U. Weiser, “MMX Technology Extension to the Intel Architecture,” IEEE Micro 16 (4), pp. 42-50, 1996.

[7] D. Marr and T. Poggio, “Cooperative computation of Stereo Disparity,” Science, Vol. 194, No. 4262, pp. 283-287, 1976.

[8] S. B. Pollard, J.E. Mayhew, J.P. Frisby, “A stereo correspondence algorithm using a disparity gradient limit,” Perception, Vol. 14, No. 4, pp. 449-470, 1985.