Robust Tracking-by-Detection using a Detector Confidence Particle Filter

被引:306
|
作者
Breitenstein, Michael D. [1 ]
Reichlin, Fabian [1 ]
Leibe, Bastian [1 ]
Koller-Meier, Esther [1 ]
Van Gool, Luc [1 ]
机构
[1] ETH, Comp Vis Lab, Zurich, Switzerland
来源
2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) | 2009年
关键词
MULTIPLE; HUMANS;
D O I
10.1109/ICCV.2009.5459278
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We propose a novel approach for multi-person tracking-by-detection in a particle filtering framework. In addition to final high-confidence detections, our algorithm uses the continuous confidence of pedestrian detectors and online trained, instance-specific classifiers as a graded observation model. Thus, generic object category knowledge is complemented by instance-specific information. A main contribution of this paper is the exploration of how these unreliable information sources can be used for multi-person tracking. The resulting algorithm robustly tracks a large number of dynamically moving persons in complex scenes with occlusions, does not rely on background modeling, and operates entirely in 2D (requiring no camera or ground plane calibration). Our Markovian approach relies only on information from the past and is suitable for online applications. We evaluate the performance on a variety of datasets and show that it improves upon state-of-the-art methods.
引用
收藏
页码:1515 / 1522
页数:8
相关论文
共 50 条
  • [21] Robust location tracking using a dual layer particle filter
    Yun, Keunho
    Kim, Daijin
    PERVASIVE AND MOBILE COMPUTING, 2007, 3 (03) : 209 - 232
  • [22] Robust motion tracking in video sequences using particle filter
    Liu, Guixi
    Fan, Chunyu
    Gao, Enke
    ADVANCES IN ARTIFICIAL REALITY AND TELE-EXISTENCE, PROCEEDINGS, 2006, 4282 : 540 - +
  • [23] A Robust Lane Detection and Tracking Based on Vanishing Point and Particle Filter
    Xu, Maopeng
    Xie, Mei
    Zhang, Daming
    PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, 2015, 322 : 677 - 685
  • [24] A Novel Tracking-by-Detection Method with Local Binary Pattern and Kalman Filter
    Zhongli Wang
    Chunxiao Jia
    Baigen Cai
    Litong Fan
    Chuanqi Tao
    Zhiyi Zhang
    Yinling Wang
    Min Zhang
    Guoyan Lyu
    Journal of Harbin Institute of Technology(New Series), 2018, 25 (03) : 74 - 87
  • [25] Pose-Guided Tracking-by-Detection: Robust Multi-Person Pose Tracking
    Bao, Qian
    Liu, Wu
    Cheng, Yuhao
    Zhou, Boyan
    Mei, Tao
    IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 : 161 - 175
  • [26] Moving Object Detection and Tracking using Particle Filter
    Ali, M. M. Naushad
    Abdullah-Al-Wadud, M.
    Lee, Seok-Lyong
    MECHATRONICS AND INDUSTRIAL INFORMATICS, PTS 1-4, 2013, 321-324 : 1200 - 1204
  • [27] Object Detection and Tracking in Video using particle filter
    Kumar, T. Senthil
    Sivanandam, S. N.
    2012 THIRD INTERNATIONAL CONFERENCE ON COMPUTING COMMUNICATION & NETWORKING TECHNOLOGIES (ICCCNT), 2012,
  • [28] Robust Feature Descriptor and Vehicle Motion Model with Tracking-by-detection for Active Safety
    Kataoka, Hirokatsu
    Tamura, Kimimasa
    Aoki, Yoshimitsu
    Matsui, Yasuhiro
    Iwata, Kenji
    Satoh, Yutaka
    39TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY (IECON 2013), 2013, : 2472 - 2477
  • [29] Cell tracking-by-detection using elliptical bounding boxes
    Kirsten, Lucas N.
    Jung, Claudio R.
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2025, 108
  • [30] Improving Multi Object Tracking-By-Detection Model Using a Temporal Interlaced Encoding and a Specialized Deep Detector
    Mhalla, Ala
    Chateau, Thierry
    2019 30TH IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV19), 2019, : 510 - 516