Zur Kurzanzeige

Semantic analysis of image sequences using computer vision methods

dc.contributor.advisorWörgötter, Florentin Prof. Dr.de
dc.contributor.authorAksoy, Eren Erdalde
dc.date.accessioned2012-10-11T15:51:42Zde
dc.date.accessioned2013-01-18T13:24:24Zde
dc.date.available2013-01-30T23:50:56Zde
dc.date.issued2012-10-11de
dc.identifier.urihttp://hdl.handle.net/11858/00-1735-0000-000D-F072-Bde
dc.identifier.urihttp://dx.doi.org/10.53846/goediss-2571
dc.format.mimetypeapplication/pdfde
dc.language.isoengde
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/de
dc.titleSemantic analysis of image sequences using computer vision methodsde
dc.typedoctoralThesisde
dc.title.translatedSemantic analysis of image sequences using computer vision methodsde
dc.contributor.refereeWörgötter, Florentin Prof. Dr.de
dc.date.examination2012-07-18de
dc.subject.dnb004 Informatikde
dc.subject.gokAllgemeine Naturwissenschaftende
dc.description.abstractengObserving, learning, and imitating human skills are intriguing topics in cognitive robotics. The main problem in the imitation learning paradigm is the policy development. Policy can be defined as a mapping from an agent's current world state to actions. Thus, understanding and performing an observed human skill for a cognitive agent depends heavily upon the learned policy. So far, naive policies that use object and hand models with trajectory information have commonly been developed to encode and imitate various types of human manipulations. These approaches, on the one hand, can not be general enough since models are not learned by the agent itself but rather are provided by the designer in advance. It is also not sufficient to imitate complicated manipulations at the trajectory-level since even the same observed manipulation can have high variations in trajectories from demonstration to demonstration. Nevertheless, humans have the capability of recognizing and imitating observed manipulations without any problem. In humans, the chain of perception, learning, and imitation of manipulations is developed in conjunction with the interpretation of the manipulated objects. To compose a human-like perception-action chain the cognitive agent needs a generic policy that can extract manipulation primitives as well as the essential (invariant) relations between objects and manipulation actions. In this thesis, we introduce a novel concept, the so-called “Semantic Event Chainde
dc.contributor.coRefereeMay, Wolfgang Prof. Dr.de
dc.subject.topicMathematics and Computer Sciencede
dc.subject.gerSemantic Event Chainsde
dc.subject.gerScene Graphsde
dc.subject.gerRelationen von Objekten und Handlungende
dc.subject.engSemantic Event Chainsde
dc.subject.engScene Graphsde
dc.subject.engObject-Action Relationsde
dc.subject.engManipulation Actionsde
dc.subject.bkInformatikde
dc.identifier.urnurn:nbn:de:gbv:7-webdoc-3735-2de
dc.identifier.purlwebdoc-3735de
dc.affiliation.instituteMathematisch-Naturwissenschaftliche Fakultätende
dc.identifier.ppn737898895de


Dateien

Thumbnail

Das Dokument erscheint in:

Zur Kurzanzeige