Download:
by Hedvig Sidenbladh, Michael J. Black
In IEEE International Conference on Computer Vision
http://www.nada.kth.se/~hedvig/publications/iccv_01.pdf
Add To MetaCart
Abstract:
This paper describes a framework for learning probabilistic models of objects and scenes and for exploiting these models for tracking complex, deformable, or articulated objects in image sequences. We focus on the probabilistic tracking of people and learn models of how they appear and move in images. In particular, we learn the likelihood of observing various spatial and temporal filter responses corresponding to edges, ridges, and motion differences given a model of the person. Similarly, we learn probability distributions over filter responses for general scenes that define a likelihood of observing the filter responses for arbitrary backgrounds. We then derive a probabilistic model for tracking that exploits the ratio between the likelihood that image pixels corresponding to the foreground (person) were generated by an actual person or by some unknown background. The paper extends previous work on learning image statistics and combines it with Bayesian tracking using particle filtering. By combining multiple image cues, and by using learned likelihood models, we demonstrate improved robustness and accuracy when tracking complex objects such as people in monocular image sequences with cluttered scenes and a moving camera. 1
Citations
|
778
|
Pfinder: Real-Time Tracking of the Human Body
– Wren, Azarbayejani, et al.
- 1997
|
|
576
|
Novel approach to nonlinear/non-Gaussian Bayesian state estimation
– Gordon, Salmond, et al.
- 1993
|
|
560
|
The Design and Use of Steerable Filters
– Freeman, Adelson
- 1991
|
|
466
|
Contour Tracking by Stochastic Propagation of Conditional Density
– Isard, Blake
- 1996
|
|
305
|
Real-time tracking of non-rigid objects using mean shift
– Comaniciu, Ramesh, et al.
- 2000
|
|
192
|
Stochastic tracking of 3D human figures using 2D image motion
– Sidenbladh, Black, et al.
- 2000
|
|
188
|
ICondensation: unifying low-level and high-level tracking in a stochastic framework
– Isard, Blake
- 1998
|
|
149
|
Probability distributions of optical flow
– Simoncelli, Adelson, et al.
- 1991
|
|
136
|
A multiple hypothesis approach to figure tracking
– Cham, Rehg
- 1999
|
|
132
|
Edge detection and ridge detection with automatic scale selection
– Lindeberg
- 1998
|
|
108
|
Integrated person tracking using stereo, color, and pattern detection
– Darrell, Gordon, et al.
- 1998
|
|
96
|
An active testing model for tracking roads in satellite images
– Geman, Jedynak
- 1996
|
|
93
|
Statistical Models for Images: Compression, Restoration and Synthesis
– Simoncelli
- 1997
|
|
88
|
Tracking persons in monocular image sequences
– Wachter, Nagel
- 1999
|
|
55
|
Natural image statistics and efficient coding
– Olshausen, Field
- 1996
|
|
52
|
Object localization by Bayesian correlation
– Sullivan, Blake, et al.
- 1999
|
|
40
|
Fundamental Bounds on Edge Detection: An Information Theoretic Evaluation of Different Edge Cues
– Konishi, Yuille, et al.
- 1999
|
|
34
|
A Probabilistic Background Model for Tracking
– Rittscher, Kato, et al.
- 2000
|
|
29
|
Joint probabilistic techniques for tracking multi-part objects
– Rasmussen, Hager
- 1998
|
|
26
|
Bayesian estimation of 3-d human motion from an image sequence
– Leventon, Freeman
- 1998
|
|
22
|
Learning and tracking cyclic human motion
– Ormoneit, Sidenbladh, et al.
- 2001
|
|
15
|
Statistical foreground modelling for object localisation
– Sullivan, Blake, et al.
- 2000
|
|
10
|
Random collage model for natural images
– Lee, Huang, et al.
- 2000
|
|
9
|
Joint Probabilistic Techniques for tracking multi-part objects
– Rasmussen, Hager
- 1998
|
|
8
|
Articulated motion capture by annealed particle filtering
– Deutscher, Blake, et al.
- 2000
|
|
1
|
Learning the statistics of people in images and video. submitted: IJCV
– Sidenbladh, Black
|
|
1
|
Prior learning and Gibbs reactiondiffusion. PAMI
– Zhu, Mumford
- 1997
|
