Kernel based visual tracking with reasoning about adaptive distribution image

Authors:
Risheng Han
Affiliations:
College of Mathematics, Physics and Information Engineering, Jiaxing University, Jiaxing, Zhejiang, China
Venue:
AICI'11 Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part III
Year:
2011

Citing 4
Cited 0

An Algorithm for Data-Driven Bandwidth Selection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Kernel-Based Object Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Real Time Face and Object Tracking as a Component of a Perceptual User Interface

WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Multiple Collaborative Kernel Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

A template updating reasoning engine which can deal with fundamental constraints on the spatial-temporal continuity of target's motion is proposed. By analyzing target's continuously adaptive distributions image, a voting method can estimate the tracking window's scale. In updating phase, by making further computation of likelihood of target model and candidate model, both the model and scale can be automatically updated in time. The tracking ability of KBT can be improved.