Atom Cloud Detection and Segmentation Using a Deep Neural Network
ORAL
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. The method developed performs significantly better than a more conventional method based on a standardized image analysis library (Scikit-image) both for identifying regions-of-interest and extracting Gaussian parameters.
*This work was supported by EPSRC Grant No. EP/P009565/1, the John Fell Oxford University Press (OUP) Research Fund and the Royal Society. M.K. acknowledges funding from Trinity College, University of Cambridge.
–
Publication: Atom Cloud Detection Using a Deep Neural Network; arXiv:2011.1053
Atom Cloud Detection and Segmentation Using a Deep Neural Network; Machine Learning Science and Technology, submitted
Presenters
-
Lucas Hofer
- University of Oxford
- Clarendon Laboratory, University of Oxford