Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 강민성 | - |
dc.contributor.author | 임영철 | - |
dc.date.accessioned | 2023-12-26T21:13:53Z | - |
dc.date.available | 2023-12-26T21:13:53Z | - |
dc.date.created | 2017-05-22 | - |
dc.date.issued | 2017-05-19 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/47219 | - |
dc.description.abstract | Object detection methods based on fully convolutional neural networks (FCNN), such as single shot multiple box (SSD), real-time object detection (YOLO), and region-based fully convolutional networks (R-FCN), provides better performance than previous detection methods using hand-craft features. The FCNN generates more rich feature hierarchies for accurate object detection by establishing several convolution and pooling layers. These methods aim to detect and localizes multi-class objects in images by training classification and box regression models. In this paper, we focus on improving pedestrian detection performance by integrating a FCNN-based object detection method and a hand-craft feature-based method. | - |
dc.language | Korean | - |
dc.publisher | 한국자동차공학회 | - |
dc.title | FCNN 기반 보행자 검출을 위한 성능 향상 방법 | - |
dc.title.alternative | Performance Improvement Method for Fully Convolutional neural network based Pedestrian Detection | - |
dc.type | Conference Paper | - |
dc.identifier.bibliographicCitation | 2017년 한국자동차공학회 춘계학술대회, pp.535 - 537 | - |
dc.identifier.url | https://www.dbpia.co.kr/Journal/ArticleDetail/NODE07204812 | - |
dc.citation.conferencePlace | KO | - |
dc.citation.conferencePlace | 제주도 | - |
dc.citation.endPage | 537 | - |
dc.citation.startPage | 535 | - |
dc.citation.title | 2017년 한국자동차공학회 춘계학술대회 | - |
There are no files associated with this item.