Atom cloud detection and segmentation using a deep neural network
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 a...
| Автори: | , , , , |
|---|---|
| Формат: | Journal article |
| Мова: | English |
| Опубліковано: |
IOP Publishing
2021
|
| _version_ | 1826288535563403264 |
|---|---|
| author | Hofer, LR Krstajić, M Juhász, P Marchant, AL Smith, RP |
| author_facet | Hofer, LR Krstajić, M Juhász, P Marchant, AL Smith, RP |
| author_sort | Hofer, LR |
| collection | OXFORD |
| description | 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. |
| first_indexed | 2024-03-07T02:15:10Z |
| format | Journal article |
| id | oxford-uuid:a1f857a5-2258-4bf5-9433-de96bdcc4dba |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T02:15:10Z |
| publishDate | 2021 |
| publisher | IOP Publishing |
| record_format | dspace |
| spelling | oxford-uuid:a1f857a5-2258-4bf5-9433-de96bdcc4dba2022-03-27T02:17:01ZAtom cloud detection and segmentation using a deep neural networkJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:a1f857a5-2258-4bf5-9433-de96bdcc4dbaEnglishSymplectic ElementsIOP Publishing2021Hofer, LRKrstajić, MJuhász, PMarchant, ALSmith, RPWe 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. |
| spellingShingle | Hofer, LR Krstajić, M Juhász, P Marchant, AL Smith, RP Atom cloud detection and segmentation using a deep neural network |
| title | Atom cloud detection and segmentation using a deep neural network |
| title_full | Atom cloud detection and segmentation using a deep neural network |
| title_fullStr | Atom cloud detection and segmentation using a deep neural network |
| title_full_unstemmed | Atom cloud detection and segmentation using a deep neural network |
| title_short | Atom cloud detection and segmentation using a deep neural network |
| title_sort | atom cloud detection and segmentation using a deep neural network |
| work_keys_str_mv | AT hoferlr atomclouddetectionandsegmentationusingadeepneuralnetwork AT krstajicm atomclouddetectionandsegmentationusingadeepneuralnetwork AT juhaszp atomclouddetectionandsegmentationusingadeepneuralnetwork AT marchantal atomclouddetectionandsegmentationusingadeepneuralnetwork AT smithrp atomclouddetectionandsegmentationusingadeepneuralnetwork |