Experimental results on using artificial neural networks for accurate centroiding in Shack-Hartmann wavefront sensors with elongated spots

Amokrane Berdja; Eduardo Garcés Santibañez; Christian Dani Guzmán

doi:10.1117/12.2233039

27 July 2016 Experimental results on using artificial neural networks for accurate centroiding in Shack-Hartmann wavefront sensors with elongated spots

Amokrane Berdja, Eduardo Garcés Santibañez, Christian Dani Guzmán

Author Affiliations +

Proceedings Volume 9909, Adaptive Optics Systems V; 99093Y (2016) https://doi.org/10.1117/12.2233039
Event: SPIE Astronomical Telescopes + Instrumentation, 2016, Edinburgh, United Kingdom

Abstract

We introduced the use of Artificial Neural Networks (ANN) for centroiding in Shack-Hartmann wavefront sensors in the presence of elongated spots, as it will occur in Extremely Large Telescopes. We showed in simulation that ANNs can outperform existing techniques, such as the Matched Filter. The main advantage of our technique is its ability to cope with changing conditions, as real atmospheric turbulence behaves. Here we present experimental results from the laboratory that confirm the findings in our original article, while at the same time they are useful to refine the ANN-based techniques.

Citation Download Citation

Amokrane Berdja, Eduardo Garcés Santibañez, and Christian Dani Guzmán "Experimental results on using artificial neural networks for accurate centroiding in Shack-Hartmann wavefront sensors with elongated spots", Proc. SPIE 9909, Adaptive Optics Systems V, 99093Y (27 July 2016); https://doi.org/10.1117/12.2233039

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available