강건한 CNN기반 수중 물체 인식을 위한 이미지 합성과 자동화된 Annotation Tool
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 전명환 | - |
dc.contributor.author | 이영준 | - |
dc.contributor.author | 신영식 | - |
dc.contributor.author | 장혜수 | - |
dc.contributor.author | 여태경 | - |
dc.contributor.author | 김아영 | - |
dc.date.accessioned | 2023-12-22T09:31:48Z | - |
dc.date.available | 2023-12-22T09:31:48Z | - |
dc.date.issued | 2019-06 | - |
dc.identifier.uri | https://www.kriso.re.kr/sciwatch/handle/2021.sw.kriso/9270 | - |
dc.description.abstract | In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments. | - |
dc.format.extent | 11 | - |
dc.language | 한국어 | - |
dc.language.iso | KOR | - |
dc.publisher | 한국로봇학회 | - |
dc.title | 강건한 CNN기반 수중 물체 인식을 위한 이미지 합성과 자동화된 Annotation Tool | - |
dc.title.alternative | Synthesizing Image and Automated Annotation Tool for CNN based Under Water Object Detection | - |
dc.type | Article | - |
dc.publisher.location | 대한민국 | - |
dc.identifier.doi | 10.7746/jkros.2019.14.2.139 | - |
dc.identifier.bibliographicCitation | 한국로봇학회 논문지, v.14, no.2, pp 139 - 149 | - |
dc.citation.title | 한국로봇학회 논문지 | - |
dc.citation.volume | 14 | - |
dc.citation.number | 2 | - |
dc.citation.startPage | 139 | - |
dc.citation.endPage | 149 | - |
dc.description.isOpenAccess | N | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Data annotation | - |
dc.subject.keywordAuthor | Object detection | - |
dc.subject.keywordAuthor | 3D CAD model | - |
dc.subject.keywordAuthor | Underwater | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(34103) 대전광역시 유성구 유성대로1312번길 32042-866-3114
COPYRIGHT 2021 BY KOREA RESEARCH INSTITUTE OF SHIPS & OCEAN ENGINEERING. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.