A Nonparametric Treatment for Location/Segmentation Based Visual Tracking

In this paper, we address two closely related visual tracking problems: 1) localizing a target's position in low or moderate resolution videos and 2) segmenting a target's image support in moderate to high resolution videos. Both tasks are treated as an online binary classification problem using dynamic foreground/background appearance models. Our major contribution is a novel nonparametric approach that successfully maintains a temporally changing appearance model for both foreground and background. The appearance models are formulated as "bags of image patches" that approximate the true two-class appearance distributions. They are maintained using a temporaladaptive importance resampling procedure that is based on simple nonparametric statistics of the appearance patch bags. The overall framework is independent of an specific foreground/background classification process and thus offers the freedom to use different classifiers. We demonstrate the effectiveness of ...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Le Lu, Gregory D. Hager
• Keywords: Appearance Patch Bags, Computer Vision, CVPR 2007, Foreground/background Appearance Models, Moderate Resolution Videos, Specific Foreground/background Classification, Two-class Appearance Distributions