Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 강민성 | - |
dc.contributor.author | 임영철 | - |
dc.date.accessioned | 2023-12-26T20:43:04Z | - |
dc.date.available | 2023-12-26T20:43:04Z | - |
dc.date.created | 2017-11-20 | - |
dc.date.issued | 2017-11-17 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/47040 | - |
dc.description.abstract | Object detection methods based on fully convolutional neural networks (FCNN), such as single shot multiple box (SSD), real-time object detection (YOLOv2), and region-based fully convolutional networks (R-FCN), achieves top performance in recent years. Among these methods, YOLOv2 has simple and fast network architecture, but it gives relatively lower detection performance for small objects. In this paper, we propose a object detection method based on YOLOv2 architecture to improve detection performance with reduced number of parameters. The previous YOLOv2 method increases the number of parameters by using paththrough layer which concatenates two feature maps of different levels. complexity by mixing high level feature and middle level feature. Our method improves both the detection performance and memory efficiency by removing the previous paththrough layer and adding extended paththrough layer. | - |
dc.language | Korean | - |
dc.publisher | 한국자동차공학회 | - |
dc.title | 객체 검출 성능 향상을 위한 Extended paththrough layer 기반의 네트워크 | - |
dc.title.alternative | Extended paththrough layer based network to improve the object detection performance | - |
dc.type | Conference Paper | - |
dc.identifier.bibliographicCitation | 2017년 한국자동차공학회 추계학술대회, pp.671 - 676 | - |
dc.identifier.url | http://www.dbpia.co.kr/Journal/ArticleDetail/NODE07405650 | - |
dc.citation.conferencePlace | KO | - |
dc.citation.conferencePlace | 여수 | - |
dc.citation.endPage | 676 | - |
dc.citation.startPage | 671 | - |
dc.citation.title | 2017년 한국자동차공학회 추계학술대회 | - |
There are no files associated with this item.