Hierarchical vibrations for part-based recognition of complex objects
Pattern Recognition
| Hi-index | 0.00 |
We outline the development of a self-initializing kinematic tracker that automatically discovers its part appearance models from a video sequence. Through its unique combination of an existing global joint estimation technique and a robust physical deformation based local search method, the tracker is demonstrated as a novel approach to recovering 2D human joint locations and limb outlines from video sequences. Appearance models are discovered and employed through a novel use of the deformable organisms framework which we have extended to the temporal domain. Quantitative and qualitative results for a set of five test videos are provided. The results demonstrate an overall improvement in tracking performance and that the method is relatively insensitive to initialization, an important consideration in gradient descent-style search algorithms.