Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation

Author:

Cui Yiming1,Han Cheng2,Liu Dongfang2

Affiliation:

1. University of Florida, USA

2. Rochester Institute of Technology, USA

Abstract

The advancement of computer vision has pushed visual analysis tasks from still images to the video domain. In recent years, video instance segmentation, which aims to track and segment multiple objects in video frames, has drawn much attention for its potential applications in various emerging areas such as autonomous driving, intelligent transportation, and smart retail. In this paper, we propose an effective framework for instance-level visual analysis on video frames, which can simultaneously conduct object detection, instance segmentation, and multi-object tracking. The core idea of our method is collaborative multi-task learning which is achieved by a novel structure, named associative connections among detection, segmentation, and tracking task heads in an end-to-end learnable CNN. These additional connections allow information propagation across multiple related tasks, so as to benefit these tasks simultaneously. We evaluate the proposed method extensively on KITTI MOTS and MOTS Challenge datasets and obtain quite encouraging results.

Publisher

Association for Computing Machinery (ACM)

Reference107 articles.

1. PoseTrack: A Benchmark for Human Pose Estimation and Tracking

2. Ali Athar Sabarinath Mahadevan Aljoša Ošep Laura Leal-Taixé and Bastian Leibe. 2020. STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos. arXiv preprint arXiv:2003.08429(2020). Ali Athar Sabarinath Mahadevan Aljoša Ošep Laura Leal-Taixé and Bastian Leibe. 2020. STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos. arXiv preprint arXiv:2003.08429(2020).

3. Gedas Bertasius and Lorenzo Torresani. 2020. Classifying Segmenting and Tracking Object Instances in Video with Mask Propagation. In CVPR. IEEE Virtual 9739–9748. Gedas Bertasius and Lorenzo Torresani. 2020. Classifying Segmenting and Tracking Object Instances in Video with Mask Propagation. In CVPR. IEEE Virtual 9739–9748.

4. Alexey Bochkovskiy Chien-Yao Wang and Hong-Yuan Mark Liao. 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934(2020). Alexey Bochkovskiy Chien-Yao Wang and Hong-Yuan Mark Liao. 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934(2020).

5. Daniel Bolya , Chong Zhou , Fanyi Xiao , and Yong Jae Lee . 2019 . YOLACT: Real-time Instance Segmentation . In ICCV. IEEE , Seoul, Korea , 9157–9166. Daniel Bolya, Chong Zhou, Fanyi Xiao, and Yong Jae Lee. 2019. YOLACT: Real-time Instance Segmentation. In ICCV. IEEE, Seoul, Korea, 9157–9166.

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. A framework for robotic grasping of 3D objects in a tabletop environment;Multimedia Tools and Applications;2024-09-04

2. Stepwise Spatial Global-local Aggregation Networks for Autonomous Driving;ACM Journal on Autonomous Transportation Systems;2024-06-20

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3