TY - BOOK

T1 - Graphical Model MAP Inference with Continuous Label Space in Computer Vision

AU - Müller, Oliver

N1 - Dissertation

PY - 2018

Y1 - 2018

N2 - This thesis deals with monocular object tracking from video sequences. The goal is to improve tracking of previously unseen non-rigid objects under severe articulations without relying on prior information such as detailed 3D models and without expensive offline training with manual annotations. The proposed framework tracks highly articulated objects by decomposing the target object into small parts and apply online tracking. Drift, which is a fundamental problem of online trackers, is reduced by incorporating image segmentation cues and by using a novel global consistency prior. Joint tracking and segmentation is formulated as a high-order probabilistic graphical model over continuous state variables. A novel inference method is proposed, called S-PBP, combining slice sampling and particle belief propagation. It is shown that slice sampling leads to fast convergence and does not rely on hyper-parameter tuning as opposed to competing approaches based on Metropolis-Hastings or heuristi

AB - This thesis deals with monocular object tracking from video sequences. The goal is to improve tracking of previously unseen non-rigid objects under severe articulations without relying on prior information such as detailed 3D models and without expensive offline training with manual annotations. The proposed framework tracks highly articulated objects by decomposing the target object into small parts and apply online tracking. Drift, which is a fundamental problem of online trackers, is reduced by incorporating image segmentation cues and by using a novel global consistency prior. Joint tracking and segmentation is formulated as a high-order probabilistic graphical model over continuous state variables. A novel inference method is proposed, called S-PBP, combining slice sampling and particle belief propagation. It is shown that slice sampling leads to fast convergence and does not rely on hyper-parameter tuning as opposed to competing approaches based on Metropolis-Hastings or heuristi

KW - monocular object tracking

KW - 3 D models

KW - framework tracks

KW - MAPInferenz

KW - Artikulierte Objektverfolgung

KW - Markov-chain Monte-Carlo

KW - Maschinelles Sehen

KW - Produkt-Slice-Sampling

KW - Visuelle Objektverfolgung

KW - Slice-Sampling

KW - Probabilistisch graphische Modelle

KW - Poseschätzung

M3 - Dissertation

ER -