DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, E. | - |
dc.contributor.author | Kim, D. | - |
dc.date.accessioned | 2019-12-03T12:10:40Z | - |
dc.date.available | 2019-12-03T12:10:40Z | - |
dc.date.created | 2019-06-03 | - |
dc.date.issued | 2019-07 | - |
dc.identifier.issn | 0262-8856 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/100195 | - |
dc.description.abstract | This paper proposes a method that uses a deep neural network (DNN) to detect small traffic lights (TLs) in images captured by cameras mounted in vehicles. The proposed TL detector has a DNN architecture of encoder-decoder with focal regression loss; this loss function reduces loss of well-regressed easy examples. The proposed TL detector has freestyle anchor boxes that are placed at arbitrary locations in a grid cell of an input image, so it can detect small objects located at borders of the grid cell. We evaluate the proposed TL detector with a focal regression loss on two public TL datasets: Bosch small traffic light dataset, and LISA traffic lights data set. Compared to state-of-the-art TL detectors, the proposed TL detector achieves 7.19%42.03% higher mAP on the Bosch-TL dataset and 19.86%-49.16% higher AUC on the LISA-TL dataset. (C) 2019 Elsevier B.V. All rights reserved. | - |
dc.language | English | - |
dc.publisher | ELSEVIER SCIENCE BV | - |
dc.relation.isPartOf | IMAGE AND VISION COMPUTING | - |
dc.title | Accurate traffic light detection using deep neural network with focal regression loss | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.imavis.2019.04.003 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | IMAGE AND VISION COMPUTING, v.87, pp.24 - 36 | - |
dc.identifier.wosid | 000472988400003 | - |
dc.citation.endPage | 36 | - |
dc.citation.startPage | 24 | - |
dc.citation.title | IMAGE AND VISION COMPUTING | - |
dc.citation.volume | 87 | - |
dc.contributor.affiliatedAuthor | Lee, E. | - |
dc.contributor.affiliatedAuthor | Kim, D. | - |
dc.identifier.scopusid | 2-s2.0-85065713940 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.type.docType | Article | - |
dc.subject.keywordPlus | Advanced driver assistance systems | - |
dc.subject.keywordPlus | Object detection | - |
dc.subject.keywordPlus | Regression analysis | - |
dc.subject.keywordPlus | Anchor-box | - |
dc.subject.keywordPlus | Driving assistance systems | - |
dc.subject.keywordPlus | Encoder-decoder | - |
dc.subject.keywordPlus | Loss functions | - |
dc.subject.keywordPlus | Small object detection | - |
dc.subject.keywordPlus | Small objects | - |
dc.subject.keywordPlus | State of the art | - |
dc.subject.keywordPlus | Traffic light | - |
dc.subject.keywordPlus | Deep neural networks | - |
dc.subject.keywordAuthor | Advanced driving assistance system | - |
dc.subject.keywordAuthor | Deep neural network | - |
dc.subject.keywordAuthor | Focal regression loss | - |
dc.subject.keywordAuthor | Freestyle anchor box | - |
dc.subject.keywordAuthor | Small object detection | - |
dc.subject.keywordAuthor | Traffic light detection | - |
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.