Naslov
Image based meteor detection and path estimation

Autori
Novoselnik, Filip ; Grbić, Ratko ; Slišković, Dražen

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of 2016 International Conference on Smart Systems and Technologies (SST) / - Osijek : Fakultet elektrotehnike, računarstva i informacijskih tehnologija Sveučilišta Josipa Jurja Strossmayera u Osijeku, 2016, 307-312

ISBN
978-1-5090-3718-6

Skup
2016 International Conference on Smart Systems and Technologies (SST)

Mjesto i datum
Osijek, Hrvatska, 12.10.2016. - 14.10.2016

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
meteor detection ; clustering ; image filtering ; line fitting

Sažetak
Reliable detection of meteor streaks in video recordings is of great importance for numerous scientific and educational purposes. In this paper, a novel method for meteor detection and path estimation in stacked images is proposed. The method is based on a four stage pipeline. Additionally, a dataset is created which can be used for evaluation of different meteor detection algorithms. The proposed method has a high efficiency with 90% accuracy and 95% sensitivity regarding image classification in terms of meteor presence in image. The proposed method achieves a high percentage (∼93%) in meteor streak localization and path estimation as well.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA