Abstract
Globular clusters (GC) are crucial for understanding galaxy formation and evolution. However, identifying them in large imagery datasets is a time-consuming task. This prompts the development of an automated GC detection algorithm. Although GC detection is fundamentally an object detection problem, the state-of-the-art object detection algorithms are unable to produce accurate results. Motivated by how GCs are identified by astronomers, we propose a deep neural network that fuses multiple views of raw imaging data and learns a better representation of the input image. The proposed network is then combined with YOLO object detection algorithm resulting in YOLO for Globular Cluster detection (YOLO-GC) model. Experimental results based on a real catalog of GCs in the M33 Galaxy showed that the proposed multi-view representation learning technique helps improve detection performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We note that in this study we use ‘view’ to refer to a result of a mathematical transformation applied to the pixel intensity of the input image.
References
Ashman, K.M., Zepf, S.E.: Globular cluster systems. Globular Cluster Systems (2008)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
González, R.E., Munoz, R.P., Hernandez, C.A.: Galaxy detection and identification using deep learning and data augmentation. Astron. Comput. 25, 103–109 (2018)
Pence, W.D., Chiappetti, L., Page, C.G., Shaw, R.A., Stobie, E.: Definition of the flexible image transport system (fits), version 3.0. Astron. Astrophys. 524, A42 (2010)
Grishin, K., Mei, S., Ilic, S.: YOLO-CL: galaxy cluster detection in the SDSS with deep machine learning. arXiv preprint arXiv:2301.09657 (2023)
Marston, A., Hargis, J., Levay, K., Forshay, P., Mullally, S., Shaw, R. : Overview of the mikulski archive for space telescopes for the James Webb space telescope data archiving. In: Observatory Operations: Strategies, Processes, and Systems VII, vol. 10704, pp. 416–428. SPIE (2018)
Blakeslee, J.P., et al.: Surface brightness fluctuations in the hubble space telescope ACS/WFC F814W bandpass and an update on galaxy distances. Astrophys. J. 724(1), 657 (2010)
Sarajedini, A., Mancone, C.L.: A catalog of star cluster candidates in M33. Astron. J. 134(2), 447 (2007)
Ding, X., Zhang, X., Han, J., Ding, G.: Scaling up your kernels to 31x31: revisiting large kernel design in CNNs. In: Proceedings of the IEEE CVPR, pp. 11963–11975 (2022)
Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks (2017)
Henderson, P., Ferrari, V.: End-to-end training of object class detectors for mean average precision. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10115, pp. 198–213. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54193-8_13
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vision 128(2), 336–359 (2019)
Acknowledgement
We thank the National Astronomical Research Institute of Thailand (Public Organization), the Department of Computer Science, Faculty of Science, and the Graduate School at Chiang Mai University for providing computing facilities and financial support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Singlor, T., Thawatdamrongkit, P., Techa-Angkoon, P., Suwannajak, C., Bootkrajang, J. (2023). Globular Cluster Detection in M33 Using Multiple Views Representation Learning. In: Quaresma, P., Camacho, D., Yin, H., Gonçalves, T., Julian, V., Tallón-Ballesteros, A.J. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2023. IDEAL 2023. Lecture Notes in Computer Science, vol 14404. Springer, Cham. https://doi.org/10.1007/978-3-031-48232-8_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-48232-8_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48231-1
Online ISBN: 978-3-031-48232-8
eBook Packages: Computer ScienceComputer Science (R0)