Development of a simple three-dimensional machine-vision measurement system for in-process mechanical parts

Abstract

A machine-vision method was used to build a three-dimensional measurement system using a measurement algorithm and a perspective transformation. The image data from a double complementary metal oxide semiconductor were transmitted to a notebook personal computer to calculate the parameters. A three-dimensional measurement system for obtaining its feature points in the world coordinate system was used to calculate the measurement data. The experimental results were verified with a more precise measurement equipment, automatic transformer observation system. The three-dimensional measurement system introduced here was applied to two case studies. The first case considered the measurement of hole diameters, such as those found in the cylinder head of an internal combustion engine. By summarizing various experimental results based on studies of three kinds of hole designs, the maximum error was 0.373 mm and the minimum error was 0.053 mm, which is within the general range of manufacturing tolerances (6 0.5 mm) used in engineering schematics. The second case examined the measurement of certain key dimensions of an aggregate truck bed, and the results showed that the measured difference between the three-dimensional method and automatic transformer observation system is less than 1.2%. The proposed three-dimensional measurement system is inexpensive, offers an easy set up, and provides a certain amount of accuracy and stability.

Development of a Color Object Classification and Measurement System Using Machine Vision

“…In this figure, the camera was mounted at G 0 (X 0 , Y 0 , Z 0 ). The center of the image plane deviates from G 0 and is denoted by the vector r. (5) A generalized perspective transformation can be expressed as Eq. (2), which involves the transformation of the two coordinate systems.…”

“…(Color online) Generalized perspective projection model. (5) The product of ACRG is recruited as P = ACRG. A homogeneous 4 × 4 matrix representation for the P matrix can thus be described.…”

“…(4), a double camera was used to obtain two image planes, which were the left and right image planes. (5) Each of these two image planes provides six points on the sample, which correspond to each other. In Eq.…”

“…Some standard methods for camera calibration were developed in previous studies. (21,22) In this study, we combined these calibration methods to form a coordinate calibration procedure for 2D and 3D spaces using the quadratic transformation (23) and the perspective transformation, (5) respectively. This calibration procedure will be described in detail in Sects.…”

“…In a study by Ngo et al, a machine vision system using a double CMOS camera was built to measure the three-dimensional sizes of mechanical parts. (5) The image data acquired from the double CMOS camera were transmitted to a computer for the calculation of parameters. With this proposed system, the sizes of parts could be determined rapidly and accurately.…”