Regressed Importance Sampling on Manifolds for Efficient Object Tracking

被引：2
|
作者：
Porikli, Fatih [1 ]
Pan, Pan [2 ]
机构：
[1] Mitsubishi Elect Res Labs, Cambridge, MA 02139 USA
[2] Univ Illinois, Chicago, IL 60680 USA
来源：
AVSS: 2009 6TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE | 2009年
关键词：
VISUAL TRACKING; MODELS;
D O I：
10.1109/AVSS.2009.95
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In this paper, a new integrated particle filter is proposed for video object tracking. After particles are generated by importance sampling, each particle is regressed on the transformation space where the mapping function is learned offline by regression on pose manifold using Lie algebra, leading to a more effective allocation of particles. Experimental results on synthetic and real sequences clearly demonstrate the improved pose (affine) tracking performance of the proposed method compared with the original regression tracker and particle filters.
引用
收藏
页码：406 / +
页数：2
相关论文
共 50 条
  • [21] Efficient Sampling on Riemannian Manifolds via Langevin MCMC
    Cheng, Xiang
    Zhang, Jingzhao
    Sra, Suvrit
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [22] Particle filter with efficient importance sampling and mode tracking (PF-EIS-MT) and its application to landmark shape tracking
    Vaswani, Namrata
    Das, Samarjit
    CONFERENCE RECORD OF THE FORTY-FIRST ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1-5, 2007, : 720 - 724
  • [23] Sampling-Resilient Multi-Object Tracking
    Li, Zepeng
    Zhang, Dongxiang
    Wu, Sai
    Song, Mingli
    Chen, Gang
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 4, 2024, : 3297 - 3305
  • [24] ACSiamRPN: Adaptive Context Sampling for Visual Object Tracking
    Qin, Xiaofei
    Zhang, Yipeng
    Chang, Hang
    Lu, Hao
    Zhang, Xuedian
    ELECTRONICS, 2020, 9 (09) : 1 - 13
  • [25] Object tracking based on affine transform and uniform sampling
    Zhao, Peng-Peng
    Cui, Shao-Hui
    Gao, Min
    Fang, Dan
    Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2015, 23 : 777 - 783
  • [26] AutoTrack: Interactive Visual Object Tracking for Efficient Object Annotations
    Keh, Jefferson
    Cruz, Meygen
    Rivera, Maverick
    Jose, John Anthony
    Sybingco, Edwin
    Dadios, Elmer
    Madria, Wira
    Miguel, Angelimarie
    2020 IEEE 12TH INTERNATIONAL CONFERENCE ON HUMANOID, NANOTECHNOLOGY, INFORMATION TECHNOLOGY, COMMUNICATION AND CONTROL, ENVIRONMENT, AND MANAGEMENT (HNICEM), 2020,
  • [27] Domain-Shift Tracking: Online Learning and Visual Object Tracking on Smooth Manifolds
    Gu, Irene Y. H.
    Khan, Zulfiqar H.
    2014 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND INTEGRATED NETWORKS (SPIN), 2014, : 209 - 215
  • [28] 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
  • [29] Efficient object sampling via weak references
    Agesen, O
    Garthwaite, A
    ACM SIGPLAN NOTICES, 2001, 36 (01) : 121 - 126
  • [30] Learning Sampling Distributions for Efficient Object Detection
    Pang, Yanwei
    Cao, Jiale
    Li, Xuelong
    IEEE TRANSACTIONS ON CYBERNETICS, 2017, 47 (01) : 117 - 129
12345