Multi-object Tracking Method Based on Efficient Channel Attention and Switchable Atrous Convolution

被引:8
|
作者
Xiang, Xuezhi [1 ,2 ]
Ren, Wenkai [1 ,2 ]
Qiu, Yujian [1 ,2 ]
Zhang, Kaixu [1 ,2 ]
Lv, Ning [1 ,2 ]
机构
[1] Harbin Engn Univ, Sch Informat & Commun Engn, Harbin 150001, Peoples R China
[2] Minist Ind & Informat Technol, Key Lab Adv Marine Commun & Informat Technol, Harbin 150001, Peoples R China
基金
黑龙江省自然科学基金; 中国国家自然科学基金;
关键词
Multi-Object tracking; Efficient channel attention; Switchable atrous convolution; Data association;
D O I
10.1007/s11063-021-10519-5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In recent years,object detection and data association have getting remarkable progress which are the core components for multi-object tracking. In multi-object tracking field,the main strategy is tracking-by-detection. Although the detection based tracking method can get great results, it is relies on the performance of the detector. In complex scene, detector can not provide reliable results. Moreover,due to the incorrect detection results, data association process can not be trusted. Based on this motivation, this paper focuses on improving the accuracy of detection and data association. We introduce the efficient channel attention module to the backbone network, which can adaptively extract important information in images. Furthermore, we apply switchable atrous convolution in the network to dynamically adjust the receptive field according to object changes. In data association process, the appearance features with minimum occlusion are saved for each existing trajectory, which are used for re-associate after the objects are lost. Extensive experiments on MOT16,MOT17 and MOT20 challenging datasets demonstrate that our method is comparable with the state-of-the-art multi-object tracking methods.
引用
收藏
页码:2747 / 2763
页数:17
相关论文
共 50 条
  • [1] Multi-object Tracking Method Based on Efficient Channel Attention and Switchable Atrous Convolution
    Xuezhi Xiang
    Wenkai Ren
    Yujian Qiu
    Kaixu Zhang
    Ning Lv
    Neural Processing Letters, 2021, 53 : 2747 - 2763
  • [2] CSCMOT: Multi-object tracking based on channel spatial cooperative attention mechanism
    Wang, Fei
    Yan, Hao
    Zhang, Libo
    Gao, Ke
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 126
  • [3] MULTI-OBJECT TRACKING AS ATTENTION MECHANISM
    Fukui, Hiroshi
    Miyagawa, Taiki
    Morishita, Yusuke
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 505 - 509
  • [4] An Efficient Method for Monitoring Birds Based on Object Detection and Multi-Object Tracking Networks
    Chen, Xian
    Pu, Hongli
    He, Yihui
    Lai, Mengzhen
    Zhang, Daike
    Chen, Junyang
    Pu, Haibo
    ANIMALS, 2023, 13 (10):
  • [5] Multi-Object Tracking Via Multi-Attention
    Wang, Xianrui
    Ling, Hefei
    Chen, Jiazhong
    Li, Ping
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [6] Appearance Guidance Attention for Multi-Object Tracking
    Chen, Yong
    Huang, Junjie
    Liu, Huanlin
    Huang, Meiyong
    Zou, Zhibo
    IEEE ACCESS, 2021, 9 : 103184 - 103193
  • [7] Object Hypotheses as Points for Efficient Multi-Object Tracking
    Tarashima, Shuhei
    VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 5: VISAPP, 2021, : 828 - 835
  • [8] Multi-object tracking based on attention networks for Smart City system
    Zhou, Xiaolong
    Jia, Yangwei
    Bai, Cong
    Zhu, Haiping
    Chan, Sixian
    SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS, 2022, 52
  • [9] Pedestrian Multi-object Tracking Algorithm Based on Attention Feature Fusion
    Zhou, Yan
    Du, Zhennan
    Wang, Dongli
    ADVANCES IN COMPUTATIONAL INTELLIGENCE, IWANN 2023, PT I, 2023, 14134 : 105 - 118
  • [10] Attention mechanics for improving online Multi-Object Tracking
    Minh Chuong Dang
    Duc Dung Nguyen
    2022 ASIA CONFERENCE ON ALGORITHMS, COMPUTING AND MACHINE LEARNING (CACML 2022), 2022, : 200 - 205