Monocular-Vision and CAD Model Based Online Single-Axis Registration System

• Main Authors: LIN, YOU-CHENG, 林祐誠
• Other Authors: HO, CHAO-CHING
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/mg23zk

碩士 === 國立臺北科技大學 === 機械工程系機電整合碩士班 === 107 === The purpose of this study proposed a single-axis registration system based on monocular vision and CAD modelling without employing three-dimensional scanning or reconstruction techniques. The developed system uses dynamic modelling and image projection methods to achieve an estimate the single-axis rotation angle of an inspected workpiece. The estimate rotation angle of the inspected workpiece is reached using the pose of the virtual model. Dynamic modelling significantly reduces both the data storage and computing time required to match the virtual model. Through experiments we have found the average root-mean square(RMS) error between the true center location of special features within the inspected workpiece and those constructed within the virtual model was 2.19 pixels and RMS overlap rate of 96.44%. Thus, monocular vision three-dimensional workpiece registration system with a dynamic model is effectively realized.