PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
Abstract
Multiple-object tracking and segmentation (MOTS) is a novel computer vision task that aims to jointly perform multiple object tracking (MOT) and instance segmentation. In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework. To begin with, PointTrack adopts an efficient one-stage framework for instance segmentation, and learns instance embeddings by converting compact image representations to un-ordered 2D point cloud. Compared with PointTrack, our proposed PointTrack++ offers three major improvements. Firstly, in the instance segmentation stage, we adopt a semantic segmentation decoder trained with focal loss to improve the instance selection quality. Secondly, to further boost the segmentation performance, we propose a data augmentation strategy by copy-and-paste instances into training images. Finally, we introduce a better training strategy in the instance association stage to improve the distinguishability of learned instance embeddings. The resulting framework achieves the state-of-the-art performance on the 5th BMTT MOTChallenge.
Cite
@article{arxiv.2007.01549,
title = {PointTrack++ for Effective Online Multi-Object Tracking and Segmentation},
author = {Zhenbo Xu and Wei Zhang and Xiao Tan and Wei Yang and Xiangbo Su and Yuchen Yuan and Hongwu Zhang and Shilei Wen and Errui Ding and Liusheng Huang},
journal= {arXiv preprint arXiv:2007.01549},
year = {2020}
}
Comments
CVPR2020 MOTS Challenge Winner. PointTrack++ ranks first on KITTI MOTS (http://www.cvlibs.net/datasets/kitti/eval_mots.php)