Aplicación de redes neuronales de aproximación a una línea de luz para reconstrucción 3D de objetos

J.A. Muñoz Rodríguez, A. Asundi, R. Rodríguez Vera

Abstract


A technique for 3D object shape detection based on light line image processing is presented. In this process, an approximation neural network is used to reconstruct the 3D object shape. This neural network is generated using images of a light line projected onto the objects, whose dimensions are known. These images are obtained in the scanning step of the light line onto the objects. The profilometric method used by the neural network is based on the light line deformations. These deformations are measured by the Gaussian approximation method. In this technique, the 3D shape is obtained without use the parameters of the experimental set-up. It is an advantage over conventional methods of the light line projection. In this manner, the accuracy is improved due to the errors are not introduces in the system. The accuracy in this technique is deduced by the rms value. This technique is tested with simulations and real objects. Also, the time processing and accuracy results are presented.

Keywords


3D reconstruction; light line projection; approximation neural network; gaussian approximation

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


REVISTA MEXICANA DE FÍSICA, year 67, issue 2, March-April 2021. Bimonthly Journal published by Sociedad Mexicana de Física, A. C. Departamento de Física, 2º Piso, Facultad de Ciencias, Universidad Nacional Autónoma de México, Ciudad Universitaria, Alcaldía Coyacán, C.P. 04510 , Ciudad de México. Apartado Postal 70-348. Tel. (+52)55-5622-4946, https://rmf.smf.mx/ojs/rmf, e-mail: rmf@ciencias.unam.mx. Chief Editor: José Alejandro Ayala Mercado. INDAUTOR Certificate of Reserve: 04-2019-080216404400-203, ISSN: 2683-2224 (on line), 0035-001X (print), both granted by Instituto Nacional del Derecho de Autor. Responsible for the last update of this issue, Technical Staff of Sociedad Mexicana de Física, A. C., Fís. Efraín Garrido Román, 2º. Piso, Facultad de Ciencias, Universidad Nacional Autónoma de México, Ciudad Universitaria, Alcaldía Coyacán, C.P. 04510 , Ciudad de México. Date of last modification, March 1st., 2021.

The responsibility of the materials published in Revista Mexicana de Física rests solely with their authors and their content does not necessarily reflect the criteria of the Editorial Committee or the Sociedad Mexicana de Física. The total or partial reproduction of the texts hereby published is authorized as long as the complete source and the electronic address of the publications are cited.

There is no fee for article processing, submission or publication.

Revista Mexicana de Física by Sociedad Mexicana de Física, A. C. is distributed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License