Download:
by Deva Ramanan, Deva Ramanan, D. A. Forsyth, D. A. Forsyth, Andrew Zisserman, Andrew Zisserman
In Proc. CVPR
http://digitalassets.lib.berkeley.edu/techreports/ucb/text/CSD-04-1362.pdf
Add To MetaCart
Abstract:
We develop an algorithm for finding and kinematically tracking multiple people in long sequences. Our basic assumption is that people tend to take on certain canonical poses, even when performing unusual activities like throwing a baseball or figure skating. We build a person detector that quite accurately detects and localizes limbs of people in lateral walking poses. We use the estimated limbs from a detection to build a discriminative appearance model; we assume the features that discriminate a figure in one frame will discriminate the figure in other frames. We then use the models as limb detectors in a pictorial structure framework, detecting figures in unrestricted poses in both previous and successive frames. We have run our tracker on hundreds of thousands of frames, and present and apply a methodology for evaluating tracking on such a large scale. We test our tracker on real sequences including a feature-length film, an hour of footage from a public park, and various sports sequences. We find that we can quite accurately automatically find and track multiple people interacting with each other while performing fast and unusual motions. 1
Citations
|
424
|
Mean shift: A robust approach toward feature space analysis,” TPAMI 02
– Comaniciu, Meer
|
|
272
|
Tracking People with Twists and Exponential Maps
– Bregler, Malik
- 1998
|
|
247
|
I.: Articulated Body Motion Capture by Annealed Particle Filtering
– Deutscher, Blake, et al.
- 2000
|
|
187
|
Stochastic tracking of 3D human figures using 2D image motion
– Sidenbladh, Black, et al.
- 2000
|
|
172
|
Model-based vision: A program to see a walking person
– Hogg
- 1983
|
|
132
|
Example-based object detection in images by components
– Mohan, Papageorgiou, et al.
- 2001
|
|
123
|
Detecting pedestrians using patterns of motion and appearance
– Viola, Jones, et al.
- 2003
|
|
108
|
A bayesian multiple-blob tracker
– Isard, MacCormick
- 2001
|
|
73
|
Efficient matching of pictorial structures
– Felzenszwalb, Huttenlocher
- 2003
|
|
72
|
Estimating human body configurations using shape context matching
– Mori, Malik
- 2002
|
|
71
|
Incremental recognition of pedestrians from image sequences
– Rohr
- 1993
|
|
64
|
A boosted particle filter: Multitarget detection and tracking
– Okuma, Teleghani, et al.
- 2004
|
|
53
|
Human detection based on a probabilistic assembly of robust part detectors. ECCV 2004. Vol I
– Mikolajczyk, Schmid, et al.
|
|
53
|
Finding and tracking people from the bottom up
– Ramanan, Forsyth
|
|
46
|
Recovering human body configurations: combining segmentation and recognition
– Mori, Ren, et al.
|
|
46
|
Towards detection of human motion
– Song, Feng, et al.
- 2000
|
|
38
|
Recognizing and tracking human action
– Sullivan, Carlsson
- 2002
|
|
35
|
Shape context and chamfer matching in cluttered scenes
– Thayananthan, Stenger, et al.
- 2003
|
|
33
|
Human tracking with mixtures of trees
– Ioffe, Forsyth
|
|
31
|
Learning to parse pictures of people
– Ronfard, Schmid, et al.
|
|
24
|
Attractive people: Assembling loose-limbed models using nonparametric belief propagation
– Sigal, Isard, et al.
|
|
15
|
Building Roadmaps of Local Minima of Visual Models
– Sminchisescu, Triggs
- 2002
|
|
9
|
Tracking Articulated Motion with Piecewise Learned Dynamical Models
– Agarwal, Triggs
- 2004
|
|
8
|
Face detection in a video sequence - a temporal approach
– Mikolajczyk, Choudhury, et al.
- 2001
|
|
2
|
On-line selection of discriminitive tracking features
– Collins, Liu
- 2003
|
