Neural detection of spheres in images for lighting calibration - Calcul Intensif, Simulation, Optimisation Access content directly
Conference Papers Year : 2023

Neural detection of spheres in images for lighting calibration

Abstract

Accurate detection of spheres in images holds significant value for photometric 3D vision techniques such as photometric stereo. 1 These techniques require precise calibration of lighting, and sphere detection can help in the calibration process. Our proposed approach involves training neural networks to automatically detect spheres of three different material classes: matte, shiny and chrome. We get fast and accurate segmentation of spheres in images, outperforming manual segmentation in terms of speed while maintaining comparable accuracy.
Fichier principal
Vignette du fichier
QCAV_2023.pdf (21.29 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04160733 , version 1 (12-07-2023)

Identifiers

Cite

Laurent Fainsin, Jean Mélou, Lilian Calvet, Axel Carlier, Jean-Denis Durou. Neural detection of spheres in images for lighting calibration. 16th International Conference on Quality Control By Artificial Vision 2023 (QCAV 2023), Jun 2023, Albi, France. pp.47, ⟨10.1117/12.3000202⟩. ⟨hal-04160733⟩
77 View
15 Download

Altmetric

Share

Gmail Facebook X LinkedIn More