Skip to content Skip to navigation
Qualifying Exam
11/9/2016 04:00 pm
CBIM 22

Visual Tracking with Reliable Memories

Shu Wang, Dept. of Computer Science

Examination Committee: Prof. Dimitris N. Metaxas (Chair), Prof. Vladimir Pavlovic, Prof. Kostas Berkris and Prof. Desheng Zhang

Abstract

We propose a novel tracking framework, which explores temporally correlated appearance clusters across tracked samples, and then preserves reliable memories for robust visual tracking. A novel clustering method with temporal constraints is carefully designed to help our tracker retrieve good memories from a vast number of samples for accurate detection, while still ensures its real-time performance. Experiment shows that our tracker performs favorably against other state-of-the-art methods, with outstanding ability to recover from drift error in long-term tracking tasks.