Shape knowledge for segmentation and tracking

Thesis

The aim of this thesis is to provide methods for 2D segmentation and 2D/3D tracking, that are both fast and robust to imperfect image information, as caused for example by occlusions, motion blur and cluttered background. We do this by combining high level shape information with simultaneous segmentation and tracking.

We base our work on the assumption that the space of possible 2D object shapes can be either generated by projecting down known rigid 3D shapes or learned from 2D shape...

Expand abstract

Authors: Prisacariu, VA

• Publication date: 2012
• DOI: 10.5287/ora-qmzjr5ev4
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: dimensionality reduction; tracking; fasthog; 2d tracking; pwplv; leve set; pwp3d; hog; gpu; 3d tracking; gplvm; latent space
• Subjects: Image understanding