Open Access Open Access  Restricted Access Subscription or Fee Access

Computer Vision for GNSS-based Detection of the Auroral Oval Boundary

Andrei Vasiliev, Yury Yasyukevich, Aleksandr Garashchenko, Ilya Edemskiy, Artem Vesnin, Denis Sidorov

Abstract



The auroral oval is a region of footprints of the Earth’s magnetic field lines associated with high energy plasma. The high energetic charged particles penetrate into the atmosphere in this region producing irregularities. The oval origin irregularities affect the radio wave propagation degrading radio system operation. For scientific and technical tasks it is important to know the position of the oval boundaries. A technique for estimating the equatorward boundary of the auroral oval is suggested. The technique involves computer vision for data from global navigation satellite systems. First, mathematical morphology to expand data and decrease data gaps is used. Second, K-means and Otsu techniques to cluster image data is employed. Third, a boundary between two cluasters and fit a second-order curve (ellipse) to obtain a continuous boundary is found. Otsu technique results in smaller error
than K-means. Obtained technique could be useful to analyze auroral effects on navigation and telecommunication systems, as well as to monitor possible operational threats.

Keywords


optimization, machine learning, operations research, ionosphere, image segmentation, computer vision, kNN, auroral oval, sparse data, Otsu method, k-means method

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.