Abstract
2D and 3D computer vision systems are frequently being used in automated production to detect and determine the position of objects. Accuracy is important in the production industry, and computer vision systems require structured environments to function optimally. For 2D vision systems, a change in surfaces, lighting and viewpoint angles can reduce the accuracy of a method, maybe even to a degree that it will be erroneous, while for 3D vision systems, the accuracy mainly depends on the 3D laser sensors. Commercially available 3D cameras lack the precision found in high-grade 3D laser scanners, and are therefore not suited for accurate measurements in industrial use. In this paper, we show that it is possible to identify and locate objects using a combination of 2D and 3D cameras. A rough estimate of the object pose is first found using a commercially available 3D camera. Then, a robotic arm with an eye-in-hand 2D camera is used to determine the pose accurately. We show that this increases the accuracy to < 1 and < 1 . This was demonstrated in a real industrial assembly task where high accuracy is required.
Highlights
IntroductionComputer vision is frequently used in industry to increase the flexibility of automated production lines without reducing the efficiency and high accuracy that automated production requires
Computer vision is frequently used in industry to increase the flexibility of automated production lines without reducing the efficiency and high accuracy that automated production requires.Assembly applications benefit from computer vision in many ways
Tests of the assembly operation using the presented object detection procedures were performed in a robotic laboratory
Summary
Computer vision is frequently used in industry to increase the flexibility of automated production lines without reducing the efficiency and high accuracy that automated production requires. We combine existing solutions from both 2D eye-in-hand and 3D computer vision in order to detect objects more predictably and with higher accuracy than either 3D or 2D methods separately. This system uses the Computer Aided Design (CAD) model of each object to render 3D views [11] and use these to determine the position and orientation of each object with sufficient accuracy to be able to assemble the objects using a robotic arm. The paper provides experimental results of an assembly task using one 3D camera, one eye-in-hand 2D camera and two robotic arms
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have