Research Of Marked-targets Vision Measurement System

In industrial production of large-size workpiece three-dimensional measurement issues,because of the limitation of traditional measuring equipment measuring range, The actualmeasurement often requires a three-dimensional digital method to get the local geometric dataquickly at first, and then completed by surface fitting and stitching. In this paper, thedevelopment of marked-targets visual measurement system can be used to implementthree-dimensional data measurement.First to do is to analyses three-dimensional visual measurement technology and theexisting measurement system, and complete the analysis and design of marked-targets visualmeasurement system. The major functions contain parameters presetting, image preprocessing,target center location, feature matching, camera calibration, three-dimensional reconstructionand outliers rejection. The next focus on the key modules of the target center location, featurematching, camera calibration and three-dimensional reconstruction and involved algorithmsin-depth study. And determine the key algorithm of the system by analyzing and comparingthe advantages and disadvantages of the current popular design method.The system uses Microsoft Visual C++6.0as the development platform to improve theuser interaction. However, due to the key modules of the target center location, featurematching, camera calibration, and three-dimensional reconstruction involving a large numberof image processing and mathematical matrix operations, the modules were developed withthe aid of Matlab. This reduces the difficulty of system development and shortens thedevelopment cycle. On the implementation of the key modules interface, the paper begin withan analysis and compares of the VC++and Matlab mixed programming method, and thenfocus on introducing the implementation process of the system key modules interface bymixed processing based on COM component, then complete the marked-targets visualmeasurement system.Finally, the paper gives the conclusion of this study by two sets of images of the automobile molds and sculptures and the result. Experience shows the system can reduce thedependence on hardware devices, measurement environment and professional technology, andachieve high stability, high accuracy three-dimensional measurement results, it can applied todeformation calculation of the monitoring points, product quality inspection and reverseengineering and other fields.