An Improved Real-Time Object Tracking Algorithm Based on Deep Learning Features

被引：0
|
作者：
Wang, Xianyu [1 ,2 ]
LI, Cong [2 ]
LI, Heyi [3 ]
Zhang, Rui [4 ]
Liang, Zhifeng [4 ]
Wang, Hai [3 ]
机构：
[1] Xidian Univ, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China
[2] Acad Space Elect Informat Technol, Xian 710100, Peoples R China
[3] Xidian Univ, Sch Aerosp Sci & Technol, Xian 710071, Peoples R China
[4] Shaanxi Aerosp Technol Applicat Res Inst Co Ltd, Xian 710100, Peoples R China
来源：
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2023年 / E106D卷 / 05期
关键词：
object tracking; feature fusion; deep learning; model update; re-detection;
D O I：
10.1587/transinf.2022DLP0039
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Visual object tracking is always a challenging task in computer vision. During the tracking, the shape and appearance of the target may change greatly, and because of the lack of sufficient training samples, most of the online learning tracking algorithms will have performance bottlenecks. In this paper, an improved real-time algorithm based on deep learning features is proposed, which combines multi-feature fusion, multi-scale estimation, adaptive updating of target model and re-detection after target loss. The effectiveness and advantages of the proposed algorithm are proved by a large number of comparative experiments with other excellent algorithms on large benchmark datasets.
引用
收藏
页码：786 / 793
页数：8
相关论文
共 50 条
  • [1] Real-time Object Tracking Based on Improved Adversarial Learning
    Song, Bowen
    Lu, Wei
    Xing, Weiwei
    Xiang Wei
    Yang, Yuxiang
    Gao, Limin
    2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 3576 - 3581
  • [2] Real-Time Visual Object Tracking Based on Reinforcement Learning with Twin Delayed Deep Deterministic Algorithm
    Zheng, Shengjie
    Wang, Huan
    INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING: VISUAL DATA ENGINEERING, PT I, 2019, 11935 : 165 - 177
  • [3] Real-time Pedestrian Tracking based on Deep Features
    Bhola, Geetanjali
    Kathuria, Akhil
    Kumar, Deepak
    Das, Chandan
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND CONTROL SYSTEMS (ICICCS 2020), 2020, : 1101 - 1106
  • [4] Real-time Quadrilateral Object Corner Detection Algorithm Based on Deep Learning
    Zhang, Jinfeng
    Jiao, Zhibin
    An, Xiangjing
    He, Yejun
    2019 COMPUTING, COMMUNICATIONS AND IOT APPLICATIONS (COMCOMAP), 2019, : 70 - 75
  • [5] Real-time deep learning based multi object tracking of spermatozoa in fresh samples
    Thambawita, V.
    Hicks, S. A.
    Storas, A.
    Witczak, O.
    Andersen, J. M.
    Hammer, H. L.
    Halvorsen, P.
    Riegler, M. A.
    Haugen, T. B.
    HUMAN REPRODUCTION, 2022, 37 : 241 - 241
  • [6] Real-time multiple object tracking using deep learning methods
    Dimitrios Meimetis
    Ioannis Daramouskas
    Isidoros Perikos
    Ioannis Hatzilygeroudis
    Neural Computing and Applications, 2023, 35 : 89 - 118
  • [7] Real-time multiple object tracking using deep learning methods
    Meimetis, Dimitrios
    Daramouskas, Ioannis
    Perikos, Isidoros
    Hatzilygeroudis, Ioannis
    NEURAL COMPUTING & APPLICATIONS, 2023, 35 (01): : 89 - 118
  • [8] Real-Time Object Tracking Algorithm Based on Siamese Network
    Zhao, Wenjun
    Deng, Miaolei
    Cheng, Cong
    Zhang, Dexian
    APPLIED SCIENCES-BASEL, 2022, 12 (14):
  • [9] A Real-Time Tracking Algorithm for Multi-Target UAV Based on Deep Learning
    Hong, Tao
    Liang, Hongming
    Yang, Qiye
    Fang, Linquan
    Kadoch, Michel
    Cheriet, Mohamed
    REMOTE SENSING, 2023, 15 (01)
  • [10] Apple detection and counting using real-time video based on deep learning and object tracking
    Gao F.
    Wu Z.
    Suo R.
    Zhou Z.
    Li R.
    Fu L.
    Zhang Z.
    Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2021, 37 (21): : 217 - 224
12345