3D Shape-Encoded Particle Filter for Object Tracking and Its Application to Human Body Tracking

被引:5
|
作者
Moon, H. [1 ]
Chellappa, R. [2 ]
机构
[1] VideoMining Corp, State Coll, PA 16801 USA
[2] Univ Maryland, Dept Elect & Comp Engn, College Pk, MD 20742 USA
关键词
D O I
10.1155/2008/596989
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
We present a nonlinear state estimation approach using particle filters, for tracking objects whose approximate 3D shapes are known. The unnormalized conditional density for the solution to the nonlinear filtering problem leads to the Zakai equation, and is realized by the weights of the particles. The weight of a particle represents its geometric and temporal fit, which is computed bottom-up from the raw image using a shape-encoded filter. The main contribution of the paper is the design of smoothing filters for feature extraction combined with the adoption of unnormalized conditional density weights. The "shape filter" has the overall form of the predicted 2D projection of the 3D model, while the cross-section of the filter is designed to collect the gradient responses along the shape. The 3D-model-based representation is designed to emphasize the changes in 2D object shape due to motion, while de-emphasizing the variations due to lighting and other imaging conditions. We have found that the set of sparse measurements using a relatively small number of particles is able to approximate the high-dimensional state distribution very effectively. As a measure to stabilize the tracking, the amount of random diffusion is effectively adjusted using a Kalman updating of the covariance matrix. For a complex problem of human body tracking, we have successfully employed constraints derived from joint angles and walking motion. Copyright (C) 2008 H. Moon and R. Chellappa.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] 3D Shape-Encoded Particle Filter for Object Tracking and Its Application to Human Body Tracking
    H Moon
    R Chellappa
    EURASIP Journal on Image and Video Processing, 2008
  • [2] 3D object tracking using shape-encoded particle propagation
    Moon, H
    Chellappa, R
    Rosenfeld, A
    EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL II, PROCEEDINGS, 2001, : 307 - 314
  • [3] Tracking of human activities using shape-encoded particle propagation
    Moon, H
    Chellappa, R
    Rosenfeld, A
    2001 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL I, PROCEEDINGS, 2001, : 357 - 360
  • [4] Correlation-based particle filter for 3D object tracking
    Noyer, Jean-Charles
    Lanvin, Patrick
    Benjelloun, Mohammed
    INTEGRATED COMPUTER-AIDED ENGINEERING, 2009, 16 (02) : 165 - 177
  • [5] Visual object tracking in 3D with color based particle filter
    Barrera, Pablo
    Canas, Jose M.
    Matellan, Vicente
    PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 4, 2005, 4 : 200 - 203
  • [6] Tracking 3D human body using particle filter in moving monocular camera
    Kim, Sungmin
    Park, Chang-Beom
    Lee, Seong-Whan
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4, PROCEEDINGS, 2006, : 805 - +
  • [7] 3D human tracking with Gaussian process annealed particle filter
    Raskin, Leonid
    Rivlin, Ehud
    Rudzsky, Michael
    VISAPP 2007: PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOLUME IU/MTSV, 2007, : 459 - +
  • [8] 3D Human Motion Tracking Using Progressive Particle Filter
    Lin, Shih-Yao
    Chang, I-Cheng
    ADVANCES IN VISUAL COMPUTING, PT II, PROCEEDINGS, 2008, 5359 : 833 - +
  • [9] 3D human motion tracking based on a progressive particle filter
    Chang, I-Cheng
    Lin, Shih-Yao
    PATTERN RECOGNITION, 2010, 43 (10) : 3621 - 3635
  • [10] Shape based Moving Object Tracking with Particle Filter
    Islam, Md. Zahidul
    Lee, Chil-Woo
    2008 INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS, VOLS 1-4, 2008, : 592 - 595