DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, S | ko |
dc.contributor.author | Jang, GJ | ko |
dc.contributor.author | Kweon, In-So | ko |
dc.date.accessioned | 2011-08-12T02:17:12Z | - |
dc.date.available | 2011-08-12T02:17:12Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2005-12 | - |
dc.identifier.citation | PATTERN ANALYSIS AND APPLICATIONS, v.8, pp.211 - 226 | - |
dc.identifier.issn | 1433-7541 | - |
dc.identifier.uri | http://hdl.handle.net/10203/24874 | - |
dc.description.abstract | This paper presents a model of 3D object recognition motivated from the robust properties of human vision system (HVS). The HVS shows the best efficiency and robustness for an object identification task. The robust properties of the HVS are visual attention, contrast mechanism, feature binding, multi-resolution, size tuning, and part-based representation. In addition, bottom-up and top-down information are combined cooperatively. Based on these facts, a plausible computational model integrating these facts under the Monte Carlo optimization technique was proposed. In this scheme, object recognition is regarded as a parameter optimization problem. The bottom-up process is used to initialize parameters in a discriminative way; the top-down process is used to optimize them in a generative way. Experimental results show that the proposed recognition model is feasible for 3D object identification and pose estimation in visible and infrared band images. | - |
dc.description.sponsorship | This research has been supported by the Korean Ministry of Science and Technology for National Research Laboratory Program (Grant number M1-0302-00-0064), Korea. | en |
dc.language | English | - |
dc.language.iso | en_US | en |
dc.publisher | SPRINGER | - |
dc.subject | OBJECT RECOGNITION | - |
dc.subject | 3-D OBJECTS | - |
dc.subject | REPRESENTATION | - |
dc.subject | PERCEPTION | - |
dc.subject | ATTENTION | - |
dc.subject | CONTEXT | - |
dc.title | An effective 3D target recognition model imitating robust methods of the human visual system | - |
dc.type | Article | - |
dc.identifier.wosid | 000233630100001 | - |
dc.identifier.scopusid | 2-s2.0-28444476212 | - |
dc.type.rims | ART | - |
dc.citation.volume | 8 | - |
dc.citation.beginningpage | 211 | - |
dc.citation.endingpage | 226 | - |
dc.citation.publicationname | PATTERN ANALYSIS AND APPLICATIONS | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Kweon, In-So | - |
dc.contributor.nonIdAuthor | Kim, S | - |
dc.contributor.nonIdAuthor | Jang, GJ | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | robust properties of the HVS | - |
dc.subject.keywordAuthor | bottom-up | - |
dc.subject.keywordAuthor | top-down | - |
dc.subject.keywordAuthor | scene context | - |
dc.subject.keywordAuthor | shape context | - |
dc.subject.keywordAuthor | pose estimation | - |
dc.subject.keywordPlus | OBJECT RECOGNITION | - |
dc.subject.keywordPlus | 3-D OBJECTS | - |
dc.subject.keywordPlus | REPRESENTATION | - |
dc.subject.keywordPlus | PERCEPTION | - |
dc.subject.keywordPlus | ATTENTION | - |
dc.subject.keywordPlus | CONTEXT | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.