Abstract

In this paper we propose a 3D measurement system based on a structured light with a special pattern. The structured light is projected on an object by a projector. Two calibrated digital cameras are used to capture the images of projected area on the object separately. Artificial corner points generated by the structured light are detected. We defined a simple but effective feature parameter of the corner points. The corner points are clustered into several groups by adopting k-means cluster to analyze the feature parameter of corner points. We propose a stereo matching method using the cluster result and geometric constraint. A sequence of images is captured to enhance the measuring resolution. According to triangulation, the 3D point clouds are obtained from the pair of images. Experiment result demonstrated the feasibility of this 3D measuring system. The system with the advantages of high measuring precision and good robustness is highly attractive for applications in 3D measurement, 3D display and so on.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call