Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF D4 Publications :: Thesis :: Sunkel, Martin


MPI-INF D4 Publications
Show all entries of:this year (2019)last year (2018)two years ago (2017)Open in Notes
Action:login to update  Library locked

Thesis - Doctoral dissertation | @PhdThesis | Doktorarbeit


Author
Author(s)*:Sunkel, Martin
BibTeX citekey*:SunkelThesis2013
Language:English

Title, School
Title*:Statistical Part-based Models for Object Detection in Large 3D Scans
School:Universität des Saarlandes
Type of Thesis*:Doctoral dissertation
Month:September
Year:2013

Publisher
Publishers Name:Saarländische Universitäts- und Landesbibliothek (SULB)
Publishers Address:Saarbrücken

Note, Abstract, Copyright
LaTeX Abstract:3D scanning technology has matured to a point where very large scale acquisition of high resolution geometry has become feasible. However, having large quantities of 3D data poses new technical challenges. Many applications of practical use require an understanding of semantics of the acquired geometry. Consequently scene understanding plays a key role for many applications. This thesis is concerned with two core topics: 3D object detection and semantic alignment. We address the problem of efficiently detecting large quantities of objects in 3D scans according to object categories learned from sparse user annotation. Objects are modeled by a collection of smaller sub-parts and a graph structure representing part dependencies. The thesis introduces two novel approaches: A part-based chain structured Markov model and a general part-based full correlation model. Both models come with efficient detection schemes which allow for interactive run-times.
Keywords:3D object detection, 3D scan, point cloud, part-based, statistical model, Markov model, dynamic programming, machine learning
Download Access Level:Public
Download File(s):View attachments here:

Referees, Status, Dates
1. Referee:Prof. Dr. Hans-Peter Seidel
2. Referee:Dr. Michael Wand
Supervisor:Dr. Michael Wand
Status:Completed
First Lecture Title:Statistical Part-based Models for Object Detection in Large 3D Scans
Location of Lecture:Campus E14, Room 019
Date Kolloquium:17 September 2013
Chair Kolloquium:Prof. Dr. Philipp Slusallek

Correlation
MPG Unit:Max-Planck-Institut für Informatik
MPG Subunit:Computer Graphics Group
MPG Subsubunit:Statistical Geometry Processing Group
Appearance:MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort

BibTeX Entry:

@PHDTHESIS{SunkelThesis2013,
AUTHOR = {Sunkel, Martin},
TITLE = {Statistical Part-based Models for Object Detection in Large 3D Scans},
PUBLISHER = {Saarländische Universitäts- und Landesbibliothek (SULB)},
SCHOOL = {Universit{\"a}t des Saarlandes},
YEAR = {2013},
TYPE = {Doctoral dissertation}
PAGES = {121},
ADDRESS = {Saarbr{\"u}cken},
MONTH = {September},
}


Hide details for Attachment SectionAttachment Section

View attachments here:




Entry last modified by Marc Schmitt, 01/30/2014
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
[Library]
Created
09/26/2013 04:11:40 PM
Revisions
9.
8.
7.
6.
5.
Editor(s)
Marc Schmitt
Marc Schmitt
Martin Sunkel
Martin Sunkel
Martin Sunkel
Edit Dates
09.10.2013 11:46:04
09.10.2013 11:39:37
09/26/2013 04:32:02 PM
09/26/2013 04:22:21 PM
09/26/2013 04:21:07 PM