Dipolar Quantum Gases group

Abstract:

We use a deep neural network to detect and place region-of-interest boxes around ultracold atom clouds in absorption and fluorescence images---with the ability to identify and bound multiple clouds within a single image. The neural network also outputs segmentation masks that identify the size, shape and orientation of each cloud from which we extract the clouds' Gaussian parameters. This allows 2D Gaussian fits to be reliably seeded thereby enabling fully automatic image processing.

Abstract:

Advances in light shaping for optical trapping of neutral particles have led to the development of box traps for ultracold atoms and molecules. These traps have allowed the creation of homogeneous quantum gases and opened new possibilities for studies of many-body physics. They simplify the interpretation of experimental results, provide more direct connections with theory, and in some cases allow qualitatively new, hitherto impossible experiments. Here we review progress in this emerging field.