Abstract
This paper presents a new 3D information acquisition approach, which the aim is to reduce the amount of data to be processed in 3D shape recognition. This approach consists in extracting the 3D information from the deformations of the 2D lines projected on the 3D object, and transforms these deformations into a 1D signal. In order to simplify the extraction of descriptors of 3D shapes, the recognition process is consequently involved. In this framework, we developed a 3D acquisition system based on the projection of a multi-line pattern. We present in detail the different steps of the proposed approach, as well as the results obtained from each step. We describe the improvements we have made to 3D information acquisition processes.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have