Atom Cloud Detection Using a Deep Neural Network

TL;DR

This paper presents a deep neural network approach for automatic detection, segmentation, and parameter extraction of ultracold atom clouds in images, enabling fully automated image analysis.

Contribution

The novel neural network architecture can detect multiple atom clouds, produce segmentation masks, and accurately extract Gaussian parameters for automated processing.

Findings

Successfully detects multiple clouds in a single image

Produces segmentation masks for size, shape, and orientation

Enables automatic Gaussian fitting for atom cloud analysis

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.