MOTS: Multi-Object Tracking and Segmentation

• Published in: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 7934 - 7943
• Main Authors: Voigtlaender, Paul, Krause, Michael, Osep, Aljosa, Luiten, Jonathon, Sekar, Berin Balachandar Gnana, Geiger, Andreas, Leibe, Bastian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2019
• Subjects: Deep Learning ; Segmentation; Grouping and Shape; Motion and Tracking
• ISSN: 2575-7075
• DOI: 10.1109/CVPR.2019.00813

This paper extends the popular task of multi-object tracking to multi-object tracking and segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation procedure. Our new annotations comprise 65,213 pixel masks for 977 distinct objects (cars and pedestrians) in 10,870 video frames. For evaluation, we extend existing multi-object tracking metrics to this new task. Moreover, we propose a new baseline method which jointly addresses detection, tracking, and segmentation with a single convolutional network. We demonstrate the value of our datasets by achieving improvements in performance when training on MOTS annotations. We believe that our datasets, metrics and baseline will become a valuable resource towards developing multi-object tracking approaches that go beyond 2D bounding boxes. We make our annotations, code, and models available at https://www.vision.rwth-aachen.de/page/mots.