Leveraging Movement Representation from Contrastive Learning for Asteroid Detection
Issued Date
2024-12-01
Resource Type
ISSN
00046280
Scopus ID
2-s2.0-85213845589
Journal Title
Publications of the Astronomical Society of the Pacific
Volume
136
Issue
12
Rights Holder(s)
SCOPUS
Bibliographic Citation
Publications of the Astronomical Society of the Pacific Vol.136 No.12 (2024)
Suggested Citation
Kongsathitporn N., Supratak A., Noysena K., Awiphan S., Steeghs D., Pollacco D., Ulaczyk K., Lyman J., Ackley K., O’Neill D., Kumar A., Galloway D.K., Jiménez-Ibarra F., Dhillon V.S., Dyer M.J., O’Brien P., Ramsay G., Pallé E., Kotak R., Killestein T.L., Nuttall L.K., Breton R.P. Leveraging Movement Representation from Contrastive Learning for Asteroid Detection. Publications of the Astronomical Society of the Pacific Vol.136 No.12 (2024). doi:10.1088/1538-3873/ad8c83 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/102660
Title
Leveraging Movement Representation from Contrastive Learning for Asteroid Detection
Author's Affiliation
National Astronomical Research Institute of Thailand
Faculty of Science, Engineering and Medicine
University of Leicester
University of Portsmouth
Monash University
Armagh Observatory
Mahidol University
Instituto Astrofisico de Canarias
Turun yliopisto
The University of Manchester
The University of Sheffield
Faculty of Science, Engineering and Medicine
University of Leicester
University of Portsmouth
Monash University
Armagh Observatory
Mahidol University
Instituto Astrofisico de Canarias
Turun yliopisto
The University of Manchester
The University of Sheffield
Corresponding Author(s)
Other Contributor(s)
Abstract
To support asteroid-related studies, current motion detectors are utilized to select moving object candidates based on their visualizations and movements in sequences of sky exposures. However, the existing detectors encounter the manual parameter settings which require experts to assign proper parameters. Moreover, although the deep learning approach could automate the detection process, these approaches still require synthetic images and hand-engineered features to improve their performance. In this work, we propose an end-to-end deep learning model consisting of two branches. The first branch is trained with contrastive learning to extract a contrastive feature from sequences of sky exposures. This learning method encourages the model to capture a lower-dimensional representation, ensuring that sequences with moving sources (i.e., potential asteroids) are distinct from those without moving sources. The second branch is designed to learn additional features from the sky exposure sequences, which are then concatenated into the movement features before being processed by subsequent layers for the detection of asteroid candidates. We evaluate our model on sufficiently long-duration sequences and perform a comparative study with detection software. Additionally, we demonstrate the use of our model to suggest potential asteroids using photometry filtering. The proposed model outperforms the baseline model for asteroid streak detection by +7.70% of f1-score. Moreover, our study shows promising performance for long-duration sequences and improvement after adding the contrastive feature. Additionally, we demonstrate the uses of our model with the filtering to detect potential asteroids in wide-field detection using the long-duration sequences. Our model could complement the software as it suggests additional asteroids to its detection result.