- Title
- Semantic segmentation of astronomical radio images: a computer vision approach
- Creator
- Kupa, Ramadimetse Sydil
- ThesisAdvisor
- Smirnov, Oleg M
- ThesisAdvisor
- Atemkeng, Marcellin, 1986-
- ThesisAdvisor
- Thorat, Kshitji
- Subject
- Semantic segmentation
- Subject
- Radio astronomy
- Subject
- Radio telescopes
- Subject
- Deep learning (Machine learning)
- Subject
- Image segmentation
- Date
- 2023-03-29
- Type
- Academic theses
- Type
- Master's theses
- Type
- text
- Identifier
- http://hdl.handle.net/10962/422378
- Identifier
- vital:71937
- Description
- The new generation of radio telescopes, such as the MeerKAT, ASKAP (Australian Square Kilometre Array Pathfinder) and the future Square Kilometre Array (SKA), are expected to produce vast amounts of data and images in the petabyte region. Therefore, the amount of incoming data at a specific point in time will overwhelm any current traditional data analysis method being deployed. Deep learning architectures have been applied in many fields, such as, in computer vision, machine vision, natural language processing, social network filtering, speech recognition, machine translation, bioinformatics, medical image analysis, and board game programs. They have produced results which are comparable to human expert performance. Hence, it is appealing to apply it to radio astronomy data. Image segmentation is one such area where deep learning techniques are prominent. The images from the new generation of telescopes have a high density of radio sources, making it difficult to classify the sources in the image. Identifying and segmenting sources from radio images is a pre-processing step that occurs before sources are put into different classes. There is thus a need for automatic segmentation of the sources from the images before they can be classified. This work uses the Unet architecture (originally developed for biomedical image segmentation) to segment radio sources from radio astronomical images with 99.8% accuracy. After segmenting the sources we use OpenCV tools to detect the sources on the mask images, then the detection is translated to the original image where borders are drawn around each detected source. This process automates and simplifies the pre-processing of images for classification tools and any other post-processing tool that requires a specific source as an input.
- Description
- Thesis (MSc) -- Faculty of Science, Physics and Electronics, 2023
- Format
- computer, online resource, application/pdf, 1 online resource (75 pages), pdf
- Publisher
- Rhodes University, Faculty of Science, Physics and Electronics
- Language
- English
- Rights
- Kupa, Ramadimetse Sydil
- Rights
- Use of this resource is governed by the terms and conditions of the Creative Commons "Attribution-NonCommercial-ShareAlike" License (http://creativecommons.org/licenses/by-nc-sa/2.0/)
- Hits: 459
- Visitors: 471
- Downloads: 31
Collections
RU Department of Physics and Electronics
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCE1 | KUPA-MSC-TR23-72.pdf | 4 MB | Adobe Acrobat PDF | View Details Download |