Multi-face tracking based on spatio-temporal detections

被引：0
|
作者：
Martinez-Diaz, Yoanna [1 ]
Hernandez, Noslen [2 ]
Mendez-Vazquez, Heydi [1 ]
机构：
[1] Adv Technol Applicat Ctr, 7th A Ave 21406 214 & 216, Havana 12200, Cuba
[2] Pontifical Catholic Univ Rio de Janeiro, Rio De Janeiro, Brazil
来源：
INTELLIGENT DATA ANALYSIS | 2016年 / 20卷
关键词：
Face detection; face tracking; data-association; spatio-temporal representation; video;
D O I：
10.3233/IDA-160851
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Tracking-by-detection methods have become increasingly popular recently. This work presents a new multi-face tracking algorithm based on the association of detection responses given by a spatio-temporal face detector; which are considered as initial small trajectories or tracklets. An appearance model based on the spatio-termporal information is used to guide the tracker. Besides, a new adaptive Kalman filter that dynamically adjusts its parameters on the basis of the quality of the detector output is proposed. The introduced approach is evaluated on several challenging video sequences from the YouTube Faces database, achieving a very good performance.
引用
收藏
页码：S141 / S154
页数：14
相关论文
共 50 条
  • [31] Particle filters for multi-face detection and tracking with automatic clustering
    Stasiak, Lukasz
    Pacut, Andrzej
    2007 IEEE INTERNATIONAL WORKSHOP ON IMAGING SYSTEMS AND TECHNIQUES, 2007, : 245 - +
  • [32] Simple Real-time Multi-face Tracking based on Convolutional Neural Networks
    Li, Xile
    Lang, Jochen
    2018 15TH CONFERENCE ON COMPUTER AND ROBOT VISION (CRV), 2018, : 337 - 344
  • [33] Spatio-temporal Active Learning for Visual Tracking
    Liu, Chenfeng
    Zhu, Pengfei
    Hu, Qinghua
    2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [34] An Improved Spatio-temporal Context Tracking Algorithm
    Wan, Hao
    Li, Weiguang
    Ye, Guoqiang
    PROCEEDINGS OF THE 2018 13TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA 2018), 2018, : 1320 - 1325
  • [35] Contour Tracking with a Spatio-Temporal Intensity Moment
    Demi, Marcello
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (06) : 1141 - 1154
  • [36] Spatio-Temporal Trajectory Models For Target Tracking
    Fanaswala, Mustafa
    Krishnamurthy, Vikram
    2014 17TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2014,
  • [37] A unified spatio-temporal articulated model for tracking
    Lan, XY
    Huttenlocher, DP
    PROCEEDINGS OF THE 2004 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, 2004, : 722 - 729
  • [38] Multi-Channel Features Spatio-Temporal Context Learning for Visual Tracking
    Zhou, Xiaoqin
    Liu, Xiaofeng
    Yang, Chenguang
    Jiang, Aimin
    Yan, Bin
    IEEE ACCESS, 2017, 5 : 12856 - 12864
  • [39] Spatio-temporal Motion Tracking with Unsynchronized Cameras
    Elhayek, A.
    Stoll, C.
    Hasler, N.
    Kim, K. I.
    Seidel, H. -P.
    Theobalt, C.
    2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2012, : 1870 - 1877
  • [40] Spatio-Temporal Tracking of Faces by Stereo Vision
    Steffens, Markus
    Krybus, Werner
    Kohring, Christine
    Morton, Danny
    COMPUTER VISION/COMPUTER GRAPHICS COLLABORATION TECHNIQUES, PROCEEDINGS, 2009, 5496 : 242 - +
12345