Fast Online Object Tracking and Segmentation: A Unifying Approach

In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object trackin...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 1328 - 1338
Hlavní autoři:	Wang, Qiang, Zhang, Li, Bertinetto, Luca, Hu, Weiming, Torr, Philip H.S.
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 01.06.2019
Témata:	Deep Learning Motion and Tracking Vision Applications and Systems
ISSN:	1063-6919
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state-of-the-art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017.
ISSN:	1063-6919
DOI:	10.1109/CVPR.2019.00142