Abstract:
Tree-structured probabilistic models admit simple, fast inference. However, they are not well suited to phenomena such as occlusion, where multiple components of an object may disappear simultaneously. Mixtures of trees appear to address this problem, at the cost of representing a large mixture. We demonstrate an efficient and compact representation of this mixture, which admits simple learning and inference algorithms. We use this method to build an automated tracker for Muybridge sequences of a variety of human activities. Tracking is difficult, because the temporal dependencies rule out simple inference methods. We show how to use our model for efficient inference, using a method that employs alternate spatial and temporal inference. The result is a tracker that (a) uses a very loose motion model, and so can track many different activities at a variable frame rate and (b) is entirely automatic. 1.
Citations
| 261 | Tracking People with Twists and Exponential Maps – Bregler, Malik - 1998 |
| 182 | Stochastic tracking of 3D human figures using 2D image motion – Sidenbladh, Black, et al. - 2000 |
| 69 | Efficient matching of pictorial structures – Felzenszwalb, Huttenlocher - 2000 |
| 45 | Towards detection of human motion – Song, Feng, et al. - 2000 |
| 27 | Finding optimum branchings – Tarjan - 1977 |
| 23 | Animals in Motion – Muybridge - 1957 |
| 21 | The human figure in motion – MUYBRIDGE - 1955 |
| 13 | Viewpoint-invariant learning and detection of human heads – Weber, Welling, et al. - 2000 |
| 1 | Learning with mixtures of trees. 2000 – Meila, Jordan |
| 1 | volume 1-7. Books Nippan, 1993-1996. A collection of photographs of human models, annotated in Japanese – file |
