elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Probabilistic Graphical Models for Object Recognition

Durner, Maximilian (2015) Probabilistic Graphical Models for Object Recognition. Master's. DLR-Interner Bericht. DLR-IB-RM-OP-2016-7, 105 S. (Unpublished)

[img] PDF - Registered users only
22MB

Abstract

Object category recognition is one of the most challenging topics in today’s computer vision. One approach which shows promising results is the ensemble of classifiers. The main benefits of such methods are the combination of task-specific expertise as well as the ability to combine multi-modal information. In this work, a new ensemble method for the task of category recognition in different environments is presented. The focus is on service robotic perception in an open environment, where the robot’s task is to recognize objects of predefined categories, based on an a priori training on a public database. The proposed concept of classifier fusion is based on the theory of a Markov Random Field (MRF). Hereby, the undirected graphical model consists of vertices representing the experts’ class-predictions and the final prediction. Since the number of the modeled relations between the nodes has a large effect on recognition accuracy and computational performance, different architectural structures are presented. By exploiting the specific characteristics of a MRF, a hybrid expert fusion method in terms of inference techniques is developed. Besides the common inference, which is considering all available experts, the MRF ensemble method can also be executed as a Dynamic Classifier Selection (DCS) system. In the experiments, the committee-dependent performance boost/decline of the proposed method, as well as the effect of a multi-modal ensemble are shown. On the basis of these observations, the benefits of the efficient dynamic inference technique are illustrated. Besides the reduction of computational effort, the ensemble either performs on the same or, in case of a strong committee, above the level of the best single expert. Finally, the impact of a cross domain application is analyzed which leads to general recommendations for adaptation in ensemble methods. Large scale evaluations were performed on two publicly available RGB-D datasets.

Item URL in elib:https://elib.dlr.de/103357/
Document Type:Monograph (DLR-Interner Bericht, Master's)
Title:Probabilistic Graphical Models for Object Recognition
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Durner, Maximilianmaximilian.durner (at) dlr.deUNSPECIFIED
Date:12 November 2015
Refereed publication:No
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Number of Pages:105
Status:Unpublished
Keywords:Markov Random Field Object Recognition
Institution:Technische Universität München
Department:Elektro- und Informationstechnik
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Technik für Raumfahrtsysteme
DLR - Research theme (Project):R - Vorhaben Multisensorielle Weltmodellierung
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Durner, Maximilian
Deposited On:21 Mar 2016 16:17
Last Modified:21 Mar 2016 16:17

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.