dc.contributor
Universitat Politècnica de Catalunya. Doctorat en Intel·ligència Artificial
dc.contributor
Universitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor
Barcelona Supercomputing Center
dc.contributor
Universitat Politècnica de Catalunya. KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic
dc.contributor.author
Pou Mulet, Bartomeu
dc.contributor.author
Quiñones Moreno, Eduardo
dc.contributor.author
Gratadour, Damien
dc.contributor.author
Martín Muñoz, Mario
dc.identifier
Pou, B. [et al.]. Denoising wavefront sensor image with deep neural networks. A: SPIE Astronomical Telescopes + Instrumentation. "Adaptive Optics Systems VII: SPIE Astronomical Telescopes + Instrumentation: 14-18 December 2020". Washington: International Society for Photo-Optical Instrumentation Engineers (SPIE), 2020, p. 1-8. DOI 10.1117/12.2576242.
dc.identifier
https://hdl.handle.net/2117/335320
dc.identifier
10.1117/12.2576242
dc.description.abstract
A classical closed-loop adaptive optics system with a Shack-Hartmann wavefront sensor (WFS) relies on a center of gravity approach to process the WFS information and an integrator with gain to produce the commands to a Deformable Mirror (DM) to compensate wavefront perturbations. In this kind of systems, noise in the WFS images can propagate to errors in centroids computation, and thus, lead the AO system to perform poorly in closed-loop operations. In this work, we present a deep supervised learning method to denoise the WFS images based on convolutional denoising autoencoders. Our method is able to denoise the images up to a high noise level and improve the integrator performance almost to the level of a noise-free situation.
dc.description.abstract
Peer Reviewed
dc.description.abstract
Postprint (author's final draft)
dc.format
application/pdf
dc.publisher
International Society for Photo-Optical Instrumentation Engineers (SPIE)
dc.relation
https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11448/2576242/Denoising-wavefront-sensor-image-with-deep-neural-networks/10.1117/12.2576242.full
dc.subject
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subject
Machine learning
dc.subject
Optical data processing
dc.subject
Machine learning in AO
dc.subject
Processament òptic de dades
dc.subject
Aprenentatge automàtic
dc.title
Denoising wavefront sensor image with deep neural networks
dc.type
Conference report
