Naslov
Measurement of Visual Activity in a Video Content Based on Computer Vision Methods of Background Subtraction

Autori
Đokić, Kristian

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

Izvornik
Infusing Research and Knowledge in South-East Europe / M. Ntika, E. Kalyva, A. Karamanos, T. Lagkas, P. Patsala, A. Prodromidou, Z. Tatsioka - Solun : SEERC Research Centre of the University of Sheffield, 2015, 383-391

ISBN
978-960-9416-08-5

Skup
10th Annual South-East European Doctoral Student Conference

Mjesto i datum
Solun, Grčka, 17.09.2015. - 18.09.2015

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
visual activity ; background subtraction ; VAI

Sažetak
This paper proposes a model for measuring video content visual activity based on a computer vision algorithm. Several authors have implied to certain trends that films and other video content have been imposing during the previous decades onwards. Firstly, the duration of shots is decreasing, the scenes are darker and there are more visual activities in films than before. To indicate and demonstrate the previous three trends, other simple models have been used by other authors. In this paper one background subtraction algorithm has been used to measure and verify increased visual activity in video content. The algorithm has been used to process the video clips of the MTV Music Awards winners, which were the winners in the category of Video of the Year in the last 30 years.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti

POVEZANOST RADA