Other
Scientific paper
May 2009
adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2009spd....40.1711m&link_type=abstract
American Astronomical Society, SPD meeting #40, #17.11; Bulletin of the American Astronomical Society, Vol. 41, p.843
Other
Scientific paper
NASA funded a large international consortium last year to produce a comprehensive system for automated feature recognition in SDO images. The data we consider are all AIA and EVE data plus surface magnetic field images from HMI. Helioseismology is addressed by another group.
We will produce robust and very efficient software modules that can keep up with the relentless SDO data stream and detect, trace, and analyze a large number of phenomena, including: flares, sigmoids, filaments, coronal dimmings, polarity inversion lines, sunspots, X-ray bright points, active regions, coronal holes, EIT waves, CME's, coronal oscillations, and jets. In addition we will track the emergence and evolution of magnetic elements down to the smallest features that are detectable, and we will also provide at least four full disk nonlinear force-free magnetic field extrapolations per day.
A completely new software element that rounds out this suite is a trainable feature detection module, which employs a generalized image classification algorithm to produce the texture features of the images analyzed. A user can introduce a number of examples of the phenomenon looked and the software will return images with similar features. We have tested a proto-type on TRACE data, and were able to "train" the algorithm to detect sunspots, active regions, and loops. Such a module can be used to find features that have not even been discovered yet, as, for example, sigmoids were in the pre-Yohkoh era.
Our codes will produce entries in the Helio Events Knowledge base, and that will permit users to locate data on individual events as well as carry out statistical studies on large numbers of events, using the interface provided by the Virtual Solar Observatory.
Angryk Rafal A.
Bernasconi Pietro N.
Cirtain Jonathan W.
Davey Alisdair R.
de Moortel Ineke
No associations
LandOfFree
Computer Vision for The Solar Dynamics Observatory does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Computer Vision for The Solar Dynamics Observatory, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Computer Vision for The Solar Dynamics Observatory will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-1112634