<div class="csl-bib-body">
<div class="csl-entry">Janusch, I., & Kropatsch, W. (2015). Novel concepts for recognition and representation of structure in spatio-temporal classes of images. In P. Wohlhart & V. Lepetit (Eds.), <i>Proceedings of the 20th Computer Vision Winter Workshop Seggau, Austria</i> (pp. 49–56). TU Graz. http://hdl.handle.net/20.500.12708/56171</div>
</div>
-
dc.identifier.isbn
978-3-85125-388-7
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/56171
-
dc.description.abstract
This paper discusses open problems and
future research regarding the recognition and rep-
resentation of structures in sequences of either 2D
images or 3D data. All presented concepts aim at
improving the recognition of structure in data (espe-
cially by decreasing the influence of noise) and at
extending the representational power of known de-
scriptors (within the scope of this paper graphs and
skeletons). For the recognition of structure critical
points of a shape may be computed. We present an
approach to derive such critical points based on a
combination of skeletons and local features along a
skeleton. We further consider classes of data (for
example a temporal sequence of images of an ob-
ject), instead of a single data sample only. This so
called co-analysis reduces the sensitivity of analysis
to noise in the data. Moreover, a representative for a
whole class can be provided. Temporal sequences
may not only be used as a class of data in a co-
analysis process - focusing on the temporal aspect
and changes of the data over time an analysis of these
changes is needed. For this purpose we explore the
possibility to analyse a shape over time and to derive
a spatio-temporal representation. To extend the rep-
resentational power of skeletons we further present
an extension to skeletons using model fitting.
en
dc.language.iso
en
-
dc.publisher
TU Graz
-
dc.title
Novel concepts for recognition and representation of structure in spatio-temporal classes of images
en
dc.type
Konferenzbeitrag
de
dc.type
Inproceedings
en
dc.relation.publication
Proceedings of the 20th Computer Vision Winter Workshop Seggau, Austria
-
dc.relation.isbn
978-3-85125-388-7
-
dc.relation.doi
10.3217/978-3-85125-388-7
-
dc.description.startpage
49
-
dc.description.endpage
56
-
dc.type.category
Full-Paper Contribution
-
dc.publisher.place
February 9 - 11, 2015
-
tuw.booktitle
Proceedings of the 20th Computer Vision Winter Workshop Seggau, Austria
-
tuw.peerreviewed
true
-
tuw.relation.publisher
Verlag der Technischen Universität Graz
-
tuw.relation.publisherplace
Graz
-
tuw.researchTopic.id
I5
-
tuw.researchTopic.name
Visual Computing and Human-Centered Technology
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E193-03 - Forschungsbereich Pattern Recognition and Image Processing
-
dc.description.numberOfPages
8
-
tuw.event.name
20 th Computer Vision Winter Workshop, CVWW 2015
-
tuw.event.startdate
09-02-2015
-
tuw.event.enddate
11-02-2015
-
tuw.event.online
On Site
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Österreich, Steiermark, Schloss Seggau
-
tuw.event.country
AT
-
tuw.event.presenter
Kropatsch, Walter
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.facultyfocus
Visual Computing and Human-Centered Technology (VC + HCT)
de
wb.facultyfocus
Visual Computing and Human-Centered Technology (VC + HCT)
en
wb.facultyfocus.faculty
E180
-
wb.presentation.type
science to science/art to art
-
item.fulltext
no Fulltext
-
item.cerifentitytype
Publications
-
item.openairecristype
http://purl.org/coar/resource_type/c_5794
-
item.languageiso639-1
en
-
item.openairetype
conference paper
-
item.grantfulltext
restricted
-
crisitem.author.dept
E186 - Institut für Computergraphik und Algorithmen
-
crisitem.author.dept
E193-03 - Forschungsbereich Virtual and Augmented Reality
-
crisitem.author.parentorg
E180 - Fakultät für Informatik
-
crisitem.author.parentorg
E193 - Institut für Visual Computing and Human-Centered Technology