Pregled bibliografske jedinice broj: 1119685
Meta-tracking and Dominant Motion Patterns at the Macroscopic Crowd Level
Meta-tracking and Dominant Motion Patterns at the Macroscopic Crowd Level // Singh S.K., Roy P., Raman B., Nagabhushan P. (eds) Computer Vision and Image Processing. CVIP 2020. Communications in Computer and Information Science, vol 1378. Springer, Singapore / Singh S.K. ; Roy P. ; Raman B. ; Nagabhushan P. (ur.).
Singapur: Springer, 2021. str. 382-393 doi:10.1007/978-981-16-1103-2_32 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1119685 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Meta-tracking and Dominant Motion Patterns at the Macroscopic Crowd Level
Autori
Matković, Franjo ; Ribarić, Slobodan
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Singh S.K., Roy P., Raman B., Nagabhushan P. (eds) Computer Vision and Image Processing. CVIP 2020. Communications in Computer and Information Science, vol 1378. Springer, Singapore
/ Singh S.K. ; Roy P. ; Raman B. ; Nagabhushan P. - Singapur : Springer, 2021, 382-393
Skup
Computer Vision and Image Processing (CVIP 2020)
Mjesto i datum
Allahābād, Indija, 04.12.2020. - 06.12.2020
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Macroscopic crowd level Crowd analysis Optical flow Particle advection Meta-trajectory Dominant motion pattern
Sažetak
This paper presents a method for crowd motion segmentation and generating dominant motion patterns at the macroscopic crowd level, where a crowd is treated as an entity. In this approach, the dominant motion patterns, as a base for behaviour analysis of a mass of people, are the focus of interest. Dominant motion patterns are generated based on meta-trajectories. A meta-trajectory is defined as a set of tracklets and/or trajectories of entities in the crowd. The entities are particles initially organized as a uniform grid which is overlaid on a flow field. To estimate the flow field, a dense optical flow is used. Based on advection of the particles, tracklets/trajectories are obtained. They are grouped by a graph-based clustering algorithm and meta-trajectories are obtained. By overlapping meta-trajectories with the quantized orientation of the average optical flow field dominant motion patterns are obtained. The preliminary experimental results of the proposed method are given for a subset of UCF dataset, a subset of Crowd Saliency Detection dataset, our own FER dataset and computer crowd simulation videos of characteristic behaviour.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
HRZZ-IP-2018-01-7619 - Pristup utemeljen na znanju za analizu mnoštva ljudi u nadzornim sustavima (KACAVIS) (Ribarić, Slobodan, HRZZ ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
