Enhancing Memory-Based Particle Filter with Detection-Based Memory Acquisition for Robustness under Severe Occlusion

• Published in: IEICE transactions on information and systems Vol. E95.D; no. 11
• Main Authors: MIKAMI, Dan, OTSUKA, Kazuhiro, KUMANO, Shiro, YAMATO, Junji
• Format: Journal Article
• Language: Japanese
• Published: 01.01.2012
• Subjects: Acquisitions; Dynamics; Marketing; Occlusion; On-line systems; Robustness; Target tracking; Tracking

A novel enhancement for the memory-based particle filter is proposed for visual pose tracking under severe occlusions. The enhancement is the addition of a detection-based memory acquisition mechanism. The memory-based particle filter, called M-PF, is a particle filter that predicts prior distributi...