当前位置: X-MOL 学术Mach. Learn. Sci. Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Atom cloud detection and segmentation using a deep neural network
Machine Learning: Science and Technology ( IF 6.013 ) Pub Date : 2021-07-13 , DOI: 10.1088/2632-2153/abf5ee
Lucas R Hofer 1 , Milan Krstajić 1, 2 , Pter Juhsz 1 , Anna L Marchant 1, 3 , Robert P Smith 1
Affiliation  

We use a deep neural network (NN) to detect and place region-of-interest (ROI) boxes around ultracold atom clouds in absorption and fluorescence images—with the ability to identify and bound multiple clouds within a single image. The NN 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 ROI and extracting Gaussian parameters.



中文翻译:

使用深度神经网络进行原子云检测和分割

我们使用深度神经网络 (NN) 在吸收和荧光图像中检测和放置超冷原子云周围的感兴趣区域 (ROI) 框,能够识别和绑定单个图像中的多个云。NN 还输出识别每个云的大小、形状和方向的分割掩码,我们从中提取云的高斯参数。这允许可靠地播种 2D 高斯拟合,从而实现全自动图像处理。所开发的方法在识别 ROI 和提取高斯参数方面的性能明显优于基于标准化图像分析库 (Scikit-image) 的更传统方法。

更新日期:2021-07-13
down
wechat
bug