You Only Stack Once : A Motion-filtered, Deep Learning Framework for Detecting Faint Moving Sources
Authors:
- Nitya PandeyNPNitya Pandey
- César FuentesCFCésar Fuentes
- Pedro BernardinelliPBPedro Bernardinelli
- Colin Orion ChandlerCCColin Orion Chandler
- David E. TrillingDTDavid E. Trilling
- Matthew J. HolmanMHMatthew J. Holman
- Steven StetzlerSSSteven Stetzler
- Dallin SpencerDSDallin Spencer
- Luis E. Salazar ManzanoLMLuis E. Salazar Manzano
- Darin RagozzineDRDarin Ragozzine
Open Access
- 19 June 2026
- journal article
- Published by American Astronomical Society in The Astronomical Journal
- Vol. 172 (1) , 34
Abstract
We present You Only Stack Once ( YOSO ), an automated pipeline designed to detect faint, slow-moving solar system objects in wide-field astronomical surveys. The pipeline integrates a novel Gaussian motion filter (GMoF) that operates at the pixel level to enhance the signal-to-noise ratio for objects exhibiting a range of apparent rates of motion. Unlike conventional shift-and-stack methods, which rely on discrete velocity trials, GMoF amplifies trails while suppressing random noise and static background features. Applied to a subset of DEEP observations from the Dark Energy Camera, YOSO discovered 45 out of 73 previously detected objects, as well as 11 new trans-Neptunian objects. It also discovered 216 objects in the near solar system. Although alternative shift-and-stack methods are sensitive to objects about 0.88 mag fainter, YOSO ’s false-positive rate is extremely low, since it detects only sources that exhibit a trail and are consistent with a point source when shifted at the right rate. We show how this method can be deployed on large surveys like LSST, and be adapted for other domains that require motion-based signal enhancement, including exoplanet imaging through angular differential imaging and near-Earth object (NEO) detection for missions like the NEO Surveyor. YOSO thus provides a versatile, scalable approach for extracting faint, motion-dependent signals in the era of data-intensive astronomy.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Detecting moving objects with machine learning2024
- The ROAD to discovery: Machine-learning-driven anomaly detection in radio astronomy spectrogramsAstronomy & Astrophysics, 2023
- Array programming with NumPyNature, 2020
- Cataloging accreted stars withinGaiaDR2 using deep learningAstronomy & Astrophysics, 2020
- SciPy 1.0: fundamental algorithms for scientific computing in PythonNature Methods, 2020
- Microsoft COCO: Common Objects in Context2014
- Astropy: A community Python package for astronomyAstronomy & Astrophysics, 2013
- A Method for Optimal Image SubtractionThe Astrophysical Journal, 1998
- SExtractor: Software for source extractionAstronomy and Astrophysics Supplement Series, 1996
- On the Origin of the Irregular SatellitesProceedings of the National Academy of Sciences, 1951