arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.03604cs.CV
收藏

MOTS:多目标跟踪和分割

MOTS: Multi-Object Tracking and Segmentation

RWTH Aachen University(亚琛工业大学);MPI for Intelligent Systems(马克斯·普朗克智能系统研究所);University of Tübingen(图宾根大学)

Paul Voigtlaender, Michael Krause, Aljosa Osep, Jonathon Luiten, Berin Balachandar Gnana Sekar, Andreas Geiger, Bastian Leibe

摘要:

本文将多目标跟踪问题扩展到多目标跟踪与分割(MOTS)。为了实现这一目标,我们使用半自动注释程序为两个现有的跟踪数据集创建密集的像素级注释。我们的新注释包括65,213个像素掩码,用于10,870个视频帧中的977个不同对象(汽车和行人)。对于评估,我们扩展现有的多对象跟踪指标,这个新的任务。此外,我们提出了一种新的基线方法,该方法通过单个卷积网络联合解决检测,跟踪和分割问题。我们通过在MOTS注释上训练时实现性能的改进来证明我们的数据集的价值。我们相信,我们的数据集、指标和基线将成为开发超越2D边界框的多目标跟踪方法的宝贵资源。我们在https://www.vision.rwth-aachen.de/page/mots上提供注释、代码和模型。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑