Institute Homepage
Institute Homepage DE Sign In

Back

Autonomous Vision Conference Paper 2019

MOTS: Multi-Object Tracking and Segmentation

pdf suppmat Project Page Poster Video Project Page
Thumb ticker sm upper body tiny
Autonomous Vision, Perceiving Systems
Andreas Geiger
Guest Scientist
Mots

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.

Author(s): Paul Voigtlaender and Michael Krause and Aljosa Osep and Jonathon Luiten and Berin Balachandar Gnana Sekar and Andreas Geiger and Bastian Leibe
Links:
Book Title: Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Year: 2019
Month: June
Bibtex Type: Conference Paper (inproceedings)
Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019
Event Place: Long Beach, USA
Electronic Archiving: grant_archive

BibTex 

@inproceedings{Voigtlaender2019CVPR,
  title = {MOTS: Multi-Object Tracking and Segmentation},
  booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  abstract = {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.},
  month = jun,
  year = {2019},
  slug = {voigtlaender2019cvpr},
  author = {Voigtlaender, Paul and Krause, Michael and Osep, Aljosa and Luiten, Jonathon and Sekar, Berin Balachandar Gnana and Geiger, Andreas and Leibe, Bastian},
  month_numeric = {6}
}