DanceCam: atmospheric turbulence mitigation in wide-field astronomical images with short-exposure video streams
arXiv:2405.05250 · doi:10.1093/mnras/stae1018
Abstract
We introduce a novel technique to mitigate the adverse effects of atmospheric turbulence on astronomical imaging. Utilizing a video-to-image neural network trained on simulated data, our method processes a sliding sequence of short-exposure (0.2s) stellar field images to reconstruct an image devoid of both turbulence and noise. We demonstrate the method with simulated and observed stellar fields, and show that the brief exposure sequence allows the network to accurately associate speckles to their originating stars and effectively disentangle light from adjacent sources across a range of seeing conditions, all while preserving flux to a lower signal-to-noise ratio than an average stack. This approach results in a marked improvement in angular resolution without compromising the astrometric stability of the final image.
arXiv commentAccepted for publication in MNRAS (advance copy available at https://doi.org/10.1093/mnras/stae1018). Project website available at https://dancecam.info/ . 20 pages, 17 figures
References in corpus (17)
- Automated Design of Deep Learning Methods for Biomedical Image Segmentation
- The Gaia mission
- Road Extraction by Deep Residual U-Net
- Global survey of star clusters in the Milky Way II. The catalogue of basic parameters
- Adaptive Optics for Astronomy
- Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
- Holographic Imaging of Crowded Fields: High Angular Resolution Imaging with Excellent Quality at Very Low Cost
- Scientific CMOS sensors in Astronomy: IMX455 and IMX411
- Convolutional Neural Networks for Transient Candidate Vetting in Large-Scale Surveys
- A New Strategy for Deep Wide-Field High Resolution Optical Imaging
- MaxiMask and MaxiTrack: two new tools for identifying contaminants in astronomical images using convolutional neural networks
- Lucky Imaging of transiting planet host stars with LuckyCam
- Astrometry with MCAO: HST-GeMS proper motions in the globular cluster NGC 6681
- Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks
- StarDICE I: sensor calibration bench and absolute photometric calibration of a Sony IMX411 sensor
- GravityCam: Wide-Field High-Resolution High-Cadence Imaging Surveys in the Visible from the Ground
- Improved Image Quality Over 10' Fields with the `Imaka Ground Layer Adaptive Optics Experiment