3D Pose Tracking Using Particle Filter with Back Projection-Based Sampling

다국어 초록 (Multilingual Abstract)

This paper explores pose tracking with a 3D object model using a particle filter. In tracking an object with a particle filter, a problem of high dimensional solution space often appears. In a huge space, a search process is tedious and falls foul of the exponential computational complexity. We propose the back projection-based sampling with a depth map from a stereo camera, which reduces the solution space significantly. In addition, we treat a method that constructs the 3D model used in this paper. Results are shown for tracking the pose of several objects.

참고문헌 (Reference)

1 K. Najim, "Trajectory tracking control based on a genealogical decision tree controller for robot manipulators" 4 (4): 53-62, 2008

2 M. Pupilli, "Real-time camera tracking using a particle filter" 519-528, 2005

3 V. Philomin, "Quasirandom sampling for condensation" 134-149, 2000

4 J. Sullivan, "Object localization by Bayesian correlation" 1068-1075, 1999

5 D. Comaniciu, "Mean shift: a robust approach toward feature space analysis" 24 (24): 603-619, 2002

6 C. L. Dirk Ormoneit, "Lattice particle filters" 395-402, 2001

7 C. Dubois, "Joint detection and tracking of time-varying harmonic components : a flexible Bayesian approach" 15 (15): 1283-1295, 2007

8 M. Isard, "Icondensation : unifying low-level and high-level tracking in a stochastic framework" 893-908, 1998

9 C. Sminchisescu, "Covariance scaled sampling for monocular 3d body tracking" 447-454, 2001

10 M. Isard, "Condensation : conditional density propagation for visual tracking" 29 (29): 5-28, 1998

11 J. Deutscher, "Articulated body motion capture by annealed particle filtering" 126-133, 2000

12 A. Blake, "Active Contours" Springer 2000

13 J. Canny, "A computational approach to edge detection" 8 (8): 679-714, 1986

14 S. D. Corhran, "3-D surface description from binocular stereo" 14 (14): 981-994, 1992