ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Towards Improved Observation Models for Visual Tracking: Selective Adaptation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Integrated Person Tracking Using Stereo, Color, and Pattern Detection
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Particle filter on GPUs for real-time tracking
SIGGRAPH '04 ACM SIGGRAPH 2004 Posters
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking
IEEE Transactions on Signal Processing
| Hi-index | 0.00 |
This paper proposed a parallel particle filter algorithm with the help of GPU (Graphic Processing Unit) in face tracking. Due to illumination and occlusion problems, face tracking usually does not work stably based on a single cue. Three different visual cues, color histogram, edge orientation histogram and wavelet feature, are integrated under the framework of particle filter to improve the tracking performance considerably. Features matches and particle weight computation have been put into GPU kernel to handle the huge amount of computation cost resulted from the introduced multi-cue strategy. Besides, an online updating strategy makes our algorithm adaptable to some slight face rotations. The experimental results demonstrate that our proposed face tracking algorithm works robustly for cluttered backgrounds and different illuminations. The GPU parallel scheme achieves a good speedup (10x∼40x) compared to the corresponding sequential algorithms.