23 September 2014 Segmentation of astronomical images
Author Affiliations +
Object detection is one of the most important procedures in astronomical imaging. This paper deals with segmentation of astronomical images based on random forrest classifier. We consider astronomical image data acquired using a photometric system with B, V, R and I filters. Each image is acquired in more realizations. All image realizations are corrected using master dark frame and master at field obtained as an average of hundreds of images. Then a profile photometry is applied to find possible position of stars. The classifier is trained by B, V, R and I image vectors. Training samples are defined by user using ellipsoidal regions (20 selections for both classes: object, background). A number of objects and their positions are compared with astronomical object catalogue using Euclidean distance. We can conclude that the performance of the presented technique is fully comparable to other SoA algorithms.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jan Švihlík, Stanislav Vítek, Karel Fliegel, Petr Páta, Elena Anisimova, "Segmentation of astronomical images", Proc. SPIE 9217, Applications of Digital Image Processing XXXVII, 921722 (23 September 2014); doi: 10.1117/12.2062009; https://doi.org/10.1117/12.2062009


Fast photometry of stars
Proceedings of SPIE (January 01 1900)
Spectroscopy using the Hadamard Transform
Proceedings of SPIE (January 27 2009)
High-speed SALT instrument CCD detectors
Proceedings of SPIE (September 29 2004)
Telescope guiding with a HyViSI H2RG used in guide mode
Proceedings of SPIE (September 17 2009)
Simultaneous seeing measurements at Atacama
Proceedings of SPIE (September 28 2004)

Back to Top