Logo image
Adaptive Video Tracking with Online Statistical Model Update
Thesis

Adaptive Video Tracking with Online Statistical Model Update

KaiYeuh Chang
Masters, 國立清華大學, 資訊工程學系
2004

Abstract

粒子濾波器 PCA 模型 視訊追蹤 particle filter PCA model visual tracking Condensation
In this thesis, we propose a statistical model-based contour tracking method based on the Condensation framework. The models include a novel contour prediction model and two statistical object models. The object models consist of the grayscale histogram and contour shape PCA models computed from the previous tracking results. With the incremental singular value decomposition (SVD) technique, these three models are learned and updated very efficiently during tracking. We show that the proposed shape prediction model performs better than the affine predictor though experiments. Experimental results show the proposed contour tracking algorithm is very stable in tracking human heads on real videos with object scaling, rotation, partial occlusion, and illumination changes.

Metrics

1 Record Views

Details

Logo image