Cosmic Ray Detection in Astronomical Images via Dictionary Learning and Sparse Representation
Bhavanam, S.R. and Channappayya, Sumohana S. and Srijith, P K and Desai, Shantanu (2022) Cosmic Ray Detection in Astronomical Images via Dictionary Learning and Sparse Representation. In: 30th European Signal Processing Conference, EUSIPCO 2022, 29 August 2022through 2 September 2022, Belgrade.
Full text not available from this repository. (Request a copy)Abstract
In this work, we propose a novel Dictionary Learning (DL) based framework to detect Cosmic Ray (CR) hits that contaminate the astronomical images obtained through optical photometric surveys. The unique and distinguishable spatial signatures of CR hits compared to other actual astrophysical sources in the image motivated us to characterize the CR patches uniquely via their sparse representations obtained from a learned dictionary. Specifically, the dictionary is trained on images acquired from the Dark Energy Camera (DECam) observations. Next, the learned dictionary is used to represent the CR and Non-CR patches (e.g., each patch is with 11×11 pixel resolution) extracted from the original images. A Machine Learning (ML) classifier is then trained to classify the CR and Non-CR patches. Empirically, we demonstrate that the proposed DL-based method can detect the CR hits at patch level and provide approximately 83% detection rates at 0.1 % false positives on the DECam test data with Random Forest (RF) algorithm. Further, we used the coarse segmentation maps obtained from the classifier output to guide the deep-learning-based CR segmentation models. The coarse maps are fed through a separate channel along with the contaminated image to detect the CR-induced pixels more accurately. We evaluated the performance of proposed DL-guided deep segmentation models over the baseline on test data from DECam. We demonstrate that the proposed method provides additional guidance to the baseline models in terms of faster convergence rate and improves CR detection performance by 2% in the case of shallow models. We made our dataset and models available at https://github.com/lfovia/Dictionary-Learning-Augmented-Cosmic-Ray-Detection. © 2022 European Signal Processing Conference, EUSIPCO. All rights reserved.
IITH Creators: |
|
||||||||
---|---|---|---|---|---|---|---|---|---|
Item Type: | Conference or Workshop Item (Paper) | ||||||||
Additional Information: | This work was supported by TCS and DST-ICPS (T-641). This project used data obtained with the Dark Energy Camera (DECam), which was constructed by the Dark Energy Survey (DES) collaboration. Funding for the DES Projects has been provided by the DOE and NSF (USA), MISE (Spain), STFC (UK), HEFCE (UK), NCSA (UIUC), KICP (U. Chicago), CCAPP (Ohio State), MIFPA (Texas A&M), CNPQ, FAPERJ, FINEP (Brazil), MINECO (Spain), DFG (Germany) and the Collaborating Institutions in the Dark Energy Survey, which are Argonne Lab, UC Santa Cruz, University of Cambridge, CIEMAT-Madrid, University of Chicago, University College London, DES-Brazil Consortium, University of Edinburgh, ETH Zürich, Fermilab, University of Illinois, ICE (IEEC-CSIC), IFAE Barcelona, Lawrence Berkeley Lab, LMU München and the associated Excellence Cluster Universe, University of Michigan, NOIRLab, University of Nottingham, Ohio State University, OzDES Membership Consortium, University of Pennsylvania, University of Portsmouth, SLAC National Lab, Stanford University, University of Sussex, and Texas A&M University. | ||||||||
Uncontrolled Keywords: | approximate K-SVD, Cosmic ray hits, dictionary learning, image processing, observational astronomy, sparse coding | ||||||||
Subjects: | Computer science Electrical Engineering Physics |
||||||||
Divisions: | Department of Computer Science & Engineering Department of Electrical Engineering Department of Physics |
||||||||
Depositing User: | . LibTrainee 2021 | ||||||||
Date Deposited: | 12 Nov 2022 10:46 | ||||||||
Last Modified: | 12 Nov 2022 10:46 | ||||||||
URI: | http://raiithold.iith.ac.in/id/eprint/11262 | ||||||||
Publisher URL: | |||||||||
Related URLs: |
Actions (login required)
View Item |
Statistics for this ePrint Item |