DC Field | Value | Language |
---|---|---|
dc.contributor.author | Su-Yong An | - |
dc.contributor.author | Jeong-Kwan Kang | - |
dc.contributor.author | Won-Seok Choi | - |
dc.contributor.author | Oh, SY | - |
dc.date.accessioned | 2016-03-31T09:03:42Z | - |
dc.date.available | 2016-03-31T09:03:42Z | - |
dc.date.created | 2012-03-28 | - |
dc.date.issued | 2011-10 | - |
dc.identifier.issn | 0924-669X | - |
dc.identifier.other | 2011-OAK-0000025308 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/16563 | - |
dc.description.abstract | In this paper, we address object recognition for a mobile robot which is deployed in a multistory building. To move to another floor, a mobile robot should recognize various objects related to an elevator, e.g., elevator control, call buttons, and LED displays. To this end, we propose a neural network based retrainable framework for object recognition, which consists of four components-preprocessing, binary classification, object identification, and outlier rejection. The binary classifier, a key component of our system, is a neural network that can be retrained, the motivation of which is to adapt to varying environments, especially with illuminations. Without incurring any extra process to prepare new training samples for retraining, they are freely obtained as a result of the outlier rejection component, being extracted on-line. To realize a practical system, we adopt a parallel architecture integrating both recognition and retraining processes for seamless object recognition, and furthermore detect and cope with the deterioration of a retrained neural network to ensure high reliability. We demonstrate the positive effect of retraining on the object recognition performance by conducting experiments over hundreds of images obtained in daytime and nighttime. | - |
dc.description.statementofresponsibility | X | - |
dc.language | English | - |
dc.publisher | SPRINGER | - |
dc.relation.isPartOf | APPLIED INTELLIGENCE | - |
dc.subject | Object recognition | - |
dc.subject | Neural network | - |
dc.subject | Graph partitioning | - |
dc.subject | On-line retraining | - |
dc.subject | NAVIGATION | - |
dc.subject | CLASSIFICATION | - |
dc.title | A neural network based retrainable framework for robust object recognition with application to mobile robotics | - |
dc.type | Article | - |
dc.contributor.college | 창의IT융합공학과 | - |
dc.identifier.doi | 10.1007/S10489-010-0212-9 | - |
dc.author.google | An, SY | - |
dc.author.google | Kang, JG | - |
dc.author.google | Choi, WS | - |
dc.author.google | Oh, SY | - |
dc.relation.volume | 35 | - |
dc.relation.issue | 2 | - |
dc.relation.startpage | 190 | - |
dc.relation.lastpage | 210 | - |
dc.contributor.id | 10071831 | - |
dc.relation.journal | APPLIED INTELLIGENCE | - |
dc.relation.index | SCI급, SCOPUS 등재논문 | - |
dc.relation.sci | SCI | - |
dc.collections.name | Journal Papers | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | APPLIED INTELLIGENCE, v.35, no.2, pp.190 - 210 | - |
dc.identifier.wosid | 000294689900003 | - |
dc.date.tcdate | 2019-01-01 | - |
dc.citation.endPage | 210 | - |
dc.citation.number | 2 | - |
dc.citation.startPage | 190 | - |
dc.citation.title | APPLIED INTELLIGENCE | - |
dc.citation.volume | 35 | - |
dc.contributor.affiliatedAuthor | Oh, SY | - |
dc.identifier.scopusid | 2-s2.0-80052961353 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.wostc | 15 | - |
dc.description.scptc | 17 | * |
dc.date.scptcdate | 2018-05-121 | * |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | Object recognition | - |
dc.subject.keywordAuthor | Neural network | - |
dc.subject.keywordAuthor | Graph partitioning | - |
dc.subject.keywordAuthor | On-line retraining | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.