Fast Online Object Tracking and Segmentation: A Unifying Approach
This work addresses the need for efficient and versatile online object tracking and segmentation in computer vision applications, offering a unified solution with high speed and accuracy.
The paper tackles real-time visual object tracking and semi-supervised video object segmentation by introducing SiamMask, a single approach that produces object segmentation masks and rotated bounding boxes at 55 frames per second, achieving state-of-the-art results on VOT-2018 and competitive performance on DAVIS datasets.
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.