Piecewise affine kernel tracking for non-planar targets
Pattern Recognition
Probabilistic fusion-based parameter estimation for visual tracking
Computer Vision and Image Understanding
Online visual tracking with histograms and articulating blocks
Computer Vision and Image Understanding
Discriminative spatial attention for robust tracking
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
A compact association of particle filtering and kernel based object tracking
Pattern Recognition
Intrackability: Characterizing Video Statistics and Pursuing Video Representations
International Journal of Computer Vision
| Hi-index | 0.00 |
This paper describes a novel approach to optimal kernel placement in kernel-based tracking. If kernels are placed at arbitrary places, kernel-based methods are likely to be trapped in ill-conditioned locations, which prevents the reliable recovery of the motion parameters and jeopardizes the tracking performance. The theoretical analysis presented in this paper indicates that the optimal kernel placement can be evaluated based on a closed-form criterion, and achieved efficiently by a novel gradient-based algorithm. Based on that, new methods for temporal-stable multiple kernel placement and scale-invariant kernel placement are proposed. These new theoretical results and new algorithms greatly advance the study of kernel-based tracking in both theory and practice. Extensive real-time experimental results demonstrate the improved tracking reliability.