DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hakkyoung Kim | - |
dc.contributor.author | Daijin Kim | - |
dc.date.accessioned | 2017-07-19T14:11:17Z | - |
dc.date.available | 2017-07-19T14:11:17Z | - |
dc.date.created | 2017-02-17 | - |
dc.date.issued | 2017-05 | - |
dc.identifier.issn | 0262-8856 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/38170 | - |
dc.description.abstract | Many existing methods for pedestrian detection have the limited detection performance in case of deformation such as large appearance variations. To overcome this limitation, we propose a novel pedestrian detection method that uses two low-level boosted features to detect pedestrians despite the presence of deformations. One is a boosted max feature (BMF) that uses a max operation to aggregate a selected pair of features to make them invariant to deformation. Another is a boosted difference feature (BDF) that uses a difference operation between a selected pair of features to improve localization accuracy of pedestrian detection. We incorporate a spatial pyramid pool method that uses multiple sized blocks to increase the richness of boosted features in a local region and use a RealBoost method to train a tree-structured classifier for the proposed pedestrian detection method. We also apply a region-of-interest method to the detected results to remove false positives effectively. Our proposed detector achieved log-average miss rates of 19.95%, 10.39%, 36.12%, and 39.57% on the Caltech-USA, INRIA, ETH, and TUD-Brussels dataset, respectively, which are the lowest among those of all state-of-the-art pedestrian detectors. (C) 2017 Elsevier B.V. All rights reserved. | - |
dc.language | English | - |
dc.publisher | ELSEVIER SCIENCE BV | - |
dc.relation.isPartOf | IMAGE AND VISION COMPUTING | - |
dc.subject | Regionlet | - |
dc.subject | Pedestrian detection | - |
dc.subject | Selective max pooling | - |
dc.subject | Selective difference pooling | - |
dc.subject | Boosted tree-structured classifier | - |
dc.title | Robust Pedestrian Detection Under Deformation Using Simple Boosted Features | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.imavis.2017.02.007 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | IMAGE AND VISION COMPUTING, v.61, pp.1 - 11 | - |
dc.identifier.wosid | 000401205700001 | - |
dc.date.tcdate | 2019-02-01 | - |
dc.citation.endPage | 11 | - |
dc.citation.startPage | 1 | - |
dc.citation.title | IMAGE AND VISION COMPUTING | - |
dc.citation.volume | 61 | - |
dc.contributor.affiliatedAuthor | Daijin Kim | - |
dc.identifier.scopusid | 2-s2.0-85014619857 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.wostc | 4 | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | Tunneling FET (TFET) | - |
dc.subject.keywordAuthor | Single Grain Boundary (SGB) | - |
dc.subject.keywordAuthor | Threshold Voltage | - |
dc.subject.keywordAuthor | Ambipolar Effect | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Software Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Optics | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Optics | - |
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.