An Online Multi-Face Tracker for Unconstrained Videos (CROSBI ID 670271)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Marčetić, Darijan ; Ribarić, Slobodan ;
engleski
An Online Multi-Face Tracker for Unconstrained Videos
This paper presents a system for online multi-face tracking in unconstrained videos. Different shooting angles, strong illumination changes, abrupt motion and face pose changes are the main characteristics of these videos. The proposed online multi-face tracking system combines deep convolutional neural network face detection, multiple instances of a tracker based on discriminative scale and space correlation filters, shot change detection, tracking failure detection, tracklet generation, and ResNet-based face identity label assignment. The system is tested on a dataset of YouTube music videos which is characterised by video sequences with great visual differences caused by face appearance variations (changes in pose, size, makeup, and illumination), and/or rapid camera motion. The results of the experiment expressed by MOTA, MOTP and IDS metrics are given and compared with state-of-the-art multi-target trackers.
Multi-face tracking, Tracking by detection, Face identity label assignment
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
159-165.
2018.
objavljeno
Podaci o matičnoj publikaciji
Proceedings SITIS 2018
New York (NY): IEEE Computer Society Conference Publishing Services
978-1-5386-9385-8
Podaci o skupu
14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS 2018)
predavanje
26.11.2018-29.11.2018
Las Palmas de Gran Canaria, Španjolska
Povezanost rada
Računarstvo