# MOTS: Multi-Object Tracking and Segmentation

## TL;DR

This paper introduces the MOTS task, extending multi-object tracking to include segmentation, supported by new datasets, metrics, and a baseline method, advancing the development of more comprehensive multi-object tracking approaches.

## Contribution

The paper creates dense pixel-level annotations for multi-object tracking datasets, extends evaluation metrics, and proposes a joint detection, tracking, and segmentation baseline method.

## Key findings

- Improved performance when training on MOTS annotations
- New pixel-level annotations for 977 objects in videos
- Extended metrics for multi-object tracking and segmentation

## 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. We make our annotations, code, and models available at https://www.vision.rwth-aachen.de/page/mots.