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. The project website is http://www.robots.ox.ac.uk/~qwang/SiamMask.
@article{arxiv.1812.05050,
title = {Fast Online Object Tracking and Segmentation: A Unifying Approach},
author = {Qiang Wang and Li Zhang and Luca Bertinetto and Weiming Hu and Philip H. S. Torr},
journal= {arXiv preprint arXiv:1812.05050},
year = {2019}
}
Comments
CVPR 2019 camera ready. Code available at https://github.com/foolwood/SiamMask