ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Jointing Recurrent Across-Channel and Spatial Attention for Multi-Object Tracking With Block-Erasing Data Augmentation

Deng, Keyu; Zhang, Congxuan*; Chen, Zhen*; Hu, Weiming; Li, Bing; Lu, Feng南昌航空大学; 中国科学院
IEEE Transactions on Circuits and Systems for Video Technology2023-8DOI: 10.1109/TCSVT.2023.3238716
1被引4阅读
引用收藏
分享

摘要

Although deep-learning-based multi-object tracking (MOT) approaches have achieved remarkable performances in terms of accuracy and efficiency, the issue of object occlusions remains an open challenge for most one-shot MOT methods. To address the problem of object occlusions, in this paper we present a recurrent across-channel and spatial attention-based one-shot multi-object tracking method with block-erasing data augmentation. First, we construct a multiattention feature learning module, named RASFL, that combines recurrent across -channel attention with spatial attention. The RASFL extracts both the correlations of the feature channels and the differences of the spatial locations to improve the accuracy of the re-identification (Re-ID) task. Second, we adopt a block-erasing data augmentation strategy to handle object occlusions by using random pixel blocks to simulate occlusion cases during the network training process. This block-erasing data augmentation assists the network to be more robust under object occlusions. By integrating the proposed RASFL module and the block-erasing data augmentation strategy into a one-shot online MOT system, we build an accurate and robust MOT model called DcMOT. Finally, we run our method on the MOT16, MOT17 and MOT20 datasets to conduct a comprehensive comparison with some of the state-of-the-art MOT methods. The experimental results demonstrate that the proposed DcMOT model achieves a competitive performance in terms of both accuracy and efficiency; with especially good performances in the occlusion cases.

学科与关键词

关键词
Multi-object trackingone shotmultiattention feature learningblock erasing strategyobject occlusions
相关
加载中…
  • Multi-Target Tracking Based on a Combined Attention Mechanism and Occlusion Sensing in a Behavior-Analysis System
    Zhou, Xiaolong; Chan, Sixian*; Qiu, Chenhao; Jiang, Xiaodan; Tang, TinglongSENSORS, 2023, 23(6): 2956.被引 1
  • Multiple Object Tracking in Deep Learning Approaches: A Survey
    Park, Yesul; Dang, L. Minh; Lee, Sujin; Han, Dongil; Moon, Hyeonjoon*Electronics, 2021, 10(19): 2406.被引 17
  • Re-identification Loss in Combination Spaces for Multiple Object Tracking
    Bai, Guangming; Deng, Chunhua*26th International Conference on Pattern Recognition / 8th International Workshop on Image Mining - Theory and Applications (IMTA), Montreal, CANADA, 2022-08-21 To 2022-08-25.
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Circuits and Systems for Video Technology
发表日期
2023-08
卷期
第 33 卷, 第 8 期
页码
4054-4069
DOI
10.1109/TCSVT.2023.3238716
语言
ENGLISH
成果收录
SCIE
资助标注
National Key Research and Development Program of China [2020YFC2003800]; National Natural Science Foundation of China [62222206, 62272209, 61866026, 61866025]; National Natural Science Foundation of Jiangxi Province [20202ACB214007]; Technology Innovation Guidance Program of Jiangxi Province [20212AEI91005]

作者

  • D

    Deng, Keyu (第一作者)

    nanchang hangkong univ

  • Z

    Zhang, Congxuan (通讯)

    nanchang hangkong univ

查看全部 6 位作者收起作者
  • C

    Chen, Zhen (通讯)

    nanchang hangkong univ

  • H

    Hu, Weiming

    chinese acad sci

  • L

    Li, Bing

    chinese acad sci

  • L

    Lu, Feng

    nanchang hangkong univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417