Real-time multi-scale parallel compressive tracking

被引:0
|
作者
Chi-Yi Tsai
Yen-Chang Feng
机构
[1] Tamkang University,Department of Electrical and Computer Engineering
来源
关键词
Robust visual tracking; Compressive tracking; Multi-scale classification; Parallel processing; Algorithmic acceleration;
D O I
暂无
中图分类号
学科分类号
摘要
Robust visual tracking is a challenging problem because the appearance of a target may rapidly change due to significant variations in the object’s motion and the surrounding illumination. In this paper, a novel robust visual tracking algorithm is proposed based on an existing compressive tracking method. The proposed algorithm adopts multiple naive Bayes classifiers, each trained under a different scale condition, to realize online parallel multi-scale classification. Further, each classifier was initialized by randomly generating different types of Haar-like features. By doing so, the robustness of the feature classification can be improved to obtain more accurate tracking results. To enhance the real-time performance of the visual tracking system, the formula of the naive Bayes classifier is studied and simplified to speed up the processing speed of parallel multi-scale feature classification. After acceleration via formula simplification and parallel implementation, the proposed visual tracking algorithm can reach a tracking performance of approximately 45 frames per second (fps) when dealing with images of 642 × 352 pixels on a popular Intel Core i5-3230M platform. The experimental results show that the proposed algorithm outperforms state-of-the-art visual tracking methods on challenging videos in terms of success rate, tracking accuracy, and visual comparison.
引用
收藏
页码:2073 / 2091
页数:18
相关论文
共 50 条
  • [21] Real-Time Architecture for a Robust Multi-Scale Stereo Engine on FPGA
    Tomasi, Matteo
    Vanegas, Mauricio
    Barranco, Francisco
    Diaz, Javier
    Ros, Eduardo
    IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2012, 20 (12) : 2208 - 2219
  • [22] The real-time fault diagnosis for transformers based on multi-scale STF
    Lv, F
    Wang, XQ
    Jiao, RP
    2003 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-5, PROCEEDINGS, 2003, : 334 - 339
  • [23] Multi-scale Lightweight Neural Network for Real-Time Object Detection
    Li, Yuan
    Wu, Qiaojun
    Chen, Song
    Kang, Yi
    PRICAI 2022: TRENDS IN ARTIFICIAL INTELLIGENCE, PT III, 2022, 13631 : 199 - 211
  • [24] A Polarizing Universal Multi-scale and Real-time Image Defogging Algorithm
    Lu Xiao-ning
    Liu Yang-yang
    Tan Zheng
    Lu Qun-bo
    ACTA PHOTONICA SINICA, 2019, 48 (08)
  • [25] Real-Time Multi-Scale Pedestrian Detection for Driver Assistance Systems
    Hemmati, Maryam
    Biglari-Abhari, Morteza
    Niar, Smail
    Berber, Stevan
    PROCEEDINGS OF THE 2017 54TH ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2017,
  • [26] MSSINet: Real-Time Segmentation Based on Multi-Scale Strip Integration
    Wang, Lin
    Zhu, Fenghua
    Zhang, Hui
    Xiong, Gang
    Huang, Yunhu
    Chen, Dewang
    IEEE JOURNAL OF RADIO FREQUENCY IDENTIFICATION, 2024, 8 : 241 - 251
  • [27] Real-Time Dense Multi-Scale Workspace Modeling on a Humanoid Robot
    Wagner, Rene
    Frese, Udo
    Baeuml, Berthold
    2013 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2013, : 5164 - 5171
  • [28] Real-Time Object Recognition Based on Cortical Multi-scale Keypoints
    Terzic, Kasim
    Rodrigues, Joao M. F.
    Hans du Buf, J. M.
    PATTERN RECOGNITION AND IMAGE ANALYSIS, IBPRIA 2013, 2013, 7887 : 314 - 321
  • [29] Multi-scale Real-time Grid Monitoring with Job Stream Mining
    Zhang, Xiangliang
    Sebag, Michele
    Germain-Renaud, Cecile
    CCGRID: 2009 9TH IEEE INTERNATIONAL SYMPOSIUM ON CLUSTER COMPUTING AND THE GRID, 2009, : 420 - 427
  • [30] Efficient Parallel Branch Network With Multi-Scale Feature Fusion for Real-Time Overhead Power Line Segmentation
    Gao, Zishu
    Yang, Guodong
    Li, En
    Liang, Zize
    Guo, Rui
    IEEE SENSORS JOURNAL, 2021, 21 (10) : 12220 - 12227