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
  • [31] Referring Multi-Object Tracking
    Wu, Dongming
    Han, Wencheng
    Wang, Tiancai
    Dong, Xingping
    Zhang, Xiangyu
    Shen, Jianbing
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 14633 - 14642
  • [32] Multi-Object Tracking in the Dark
    Wang, Xinzhe
    Ma, Kang
    Liu, Qiankun
    Zou, Yunhao
    Fu, Ying
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2024, 2024, : 382 - 392
  • [33] Multi-object trajectory tracking
    Mei Han
    Wei Xu
    Hai Tao
    Yihong Gong
    Machine Vision and Applications, 2007, 18 : 221 - 232
  • [34] Efficient Multi-Object Tracking by Strong Associations on Temporal Window
    Gunduz, Gultekin
    Acarman, Tankut
    IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2019, 4 (03): : 447 - 455
  • [35] Heterogeneous Multi-object Trajectory Prediction Method Based on Hierarchical Graph Attention
    Hu Q.
    Cai Y.
    Wang H.
    Chen L.
    Dong Z.
    Liu Q.
    Qiche Gongcheng/Automotive Engineering, 2023, 45 (08): : 1448 - 1456
  • [36] Spatial-Attention Location-Aware Multi-Object Tracking
    Han, Jun
    Li, Weixing
    Pan, Feng
    Zheng, Dongdong
    Gao, Qi
    2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 6341 - 6346
  • [37] Fusion detection and ReID embedding with hybrid attention for multi-object tracking
    Chan, Sixian
    Qiu, Chenhao
    Wu, Dijuan
    Hu, Jie
    Heidari, Ali Asghar
    Chen, Huiling
    NEUROCOMPUTING, 2024, 575
  • [38] UNet Based on Multi-Object Segmentation and Convolution Neural Network for Object Recognition
    Almujally, Nouf Abdullah
    Chughtai, Bisma Riaz
    Al Mudawi, Naif
    Alazeb, Abdulwahab
    Algarni, Asaad
    Alzahrani, Hamdan A.
    Park, Jeongmin
    CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 80 (01): : 1563 - 1580
  • [39] Improved Multi-object Detection and Tracking Method Based on Mean Shift Algorithm
    Li Jian-qiang
    Lu Hao-bo
    Du Wen-feng
    INFORMATION-AN INTERNATIONAL INTERDISCIPLINARY JOURNAL, 2011, 14 (03): : 1075 - 1080
  • [40] Multi-Object tracking using Multi-Channel Part Appearance Representation
    Nguyen Thi Lan Anh
    Khan, Furcian M.
    Negin, Farhood
    Bremond, Francois
    2017 14TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), 2017,