Visual Tracking Achieved by Adaptive Sampling from Hierarchical and Parallel Predictions

Authors:
Tomohiro Shibata;Takashi Bando;Shin Ishii
Affiliations:
Graduate School of Information Science, Nara Institute of Science and Technology,;DENSO Corporation,;Graduate School of Information Science, Nara Institute of Science and Technology, and Graduate School of Informatics, Kyoto University,
Venue:
Neural Information Processing
Year:
2007

Citing 3
Cited 0

CONDENSATION—Conditional Density Propagation forVisual Tracking

International Journal of Computer Vision
A model of smooth pursuit in primates based on learning the target dynamics

Neural Networks
On-line EM Algorithm for the Normalized Gaussian Network

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Because the inevitable ill-posedness exists in the visual information, the brain essentially needs some prior knowledge, prediction, or hypothesis to acquire a meaningful solution. From computational point of view, visual tracking is the real-time process of statistical spatiotemporal filtering of target states from an image stream, and incremental Bayesian computation is one of the most important devices. To make Bayesian computation of the posterior density of state variables tractable for any types of probability distribution, Particle Filters (PFs) have been often employed in the real-time vision area. In this paper, we briefly review incremental Bayesian computation and PFs for visual tracking, indicate drawbacks of PFs, and then propose our framework, in which hierarchical and parallel predictions are integrated by adaptive sampling to achieve appropriate balancing of tracking accuracy and robustness. Finally, we discuss the proposed model from the viewpoint of neuroscience.