Abstract

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.

Keywords

Computer scienceArtificial intelligenceSegmentationMinimum bounding boxComputer visionVideo trackingObject (grammar)Bounding overwatchImage segmentationBitTorrent trackerTask (project management)Object detectionTracking (education)Segmentation-based object categorizationScale-space segmentationEye trackingImage (mathematics)

Affiliated Institutions

Related Publications

Publication Info

Year
2019
Type
article
Citations
1497
Access
Closed

External Links

Download PDF (Free) View on DOI.org arXiv Semantic Scholar

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1497
OpenAlex
181
Influential
1150
CrossRef

Cite This

Qiang Wang, Li Zhang, Luca Bertinetto et al. (2019). Fast Online Object Tracking and Segmentation: A Unifying Approach. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . https://doi.org/10.1109/cvpr.2019.00142

Identifiers

DOI
10.1109/cvpr.2019.00142
arXiv
1812.05050

Data Quality

Data completeness: 84%