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


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.


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

Full Text:



  • There are currently no refbacks.

Revista Mexicana de Física

ISSN: 2683-2224 (on line), 0035-001X (print)

Bimonthly publication of Sociedad Mexicana de Física, A.C.
Departamento de Física, 2o. Piso, Facultad de Ciencias, UNAM.
Circuito Exterior s/n, Ciudad Universitaria. C. P. 04510 Ciudad de México.
Apartado Postal 70-348, Coyoacán, 04511 Ciudad de México.
Tel/Fax: (52) 55-5622-4946, (52) 55-5622-4840. rmf@ciencias.unam.mx