DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Jinwoo | ko |
dc.contributor.author | Park, Ji Il | ko |
dc.contributor.author | Jeon, Hyunyong | ko |
dc.contributor.author | Park, Jihyuk | ko |
dc.contributor.author | Kim, Kyung-Soo | ko |
dc.date.accessioned | 2022-12-11T05:03:15Z | - |
dc.date.available | 2022-12-11T05:03:15Z | - |
dc.date.created | 2022-12-11 | - |
dc.date.created | 2022-12-11 | - |
dc.date.issued | 2022-06 | - |
dc.identifier.citation | Journal of the Korean Society for Precision Engineering, v.39, no.6, pp.387 - 394 | - |
dc.identifier.issn | 1225-9071 | - |
dc.identifier.uri | http://hdl.handle.net/10203/302717 | - |
dc.description.abstract | Recently, in-depth studies on sensors of autonomous vehicles have been conducted. In particular, the trend to pursue only camera-based autonomous driving is progressing. Studies on object detection using IR (Infrared) cameras is essential in overcoming the limitations of the VIS (Visible) camera environment. Deep learning-based object detection technology requires sufficient data, and data augmentation can make the object detection network more robust and improve performance. In this paper, a method to increase the performance of object detection by generating and learning a highresolution image of an infrared dataset, based on a data augmentation method based on a Generative Adversarial Network (GAN) was studied. We collected data from VIS and IR cameras under severe conditions such as snowfall, fog, and heavy rain. The infrared data images from KAIST were used for data learning and verification. We confirmed that the proposed data augmentation method improved the object detection performance, by applying generated dataset to various object detection networks. Based on the study results, we plan on developing object detection technology using only cameras, by creating IR datasets from numerous VIS camera data to be secured in the future and fusion with VIS cameras. | - |
dc.language | Korean | - |
dc.publisher | Korean Society for Precision Engineeing | - |
dc.title | Data Augmentation based on Deep Learning for Object Detection of Infrared Cameras in Extreme Environments | - |
dc.title.alternative | 극한환경에서 적외선 카메라의 객체 탐지를 위한 딥러닝 기반 데이터 증강 방법에 관한 연구 | - |
dc.type | Article | - |
dc.identifier.scopusid | 2-s2.0-85132327288 | - |
dc.type.rims | ART | - |
dc.citation.volume | 39 | - |
dc.citation.issue | 6 | - |
dc.citation.beginningpage | 387 | - |
dc.citation.endingpage | 394 | - |
dc.citation.publicationname | Journal of the Korean Society for Precision Engineering | - |
dc.identifier.doi | 10.7736/JKSPE.022.026 | - |
dc.identifier.kciid | ART002845473 | - |
dc.contributor.localauthor | Kim, Kyung-Soo | - |
dc.contributor.nonIdAuthor | Cho, Jinwoo | - |
dc.contributor.nonIdAuthor | Park, Jihyuk | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | 데이터 증강 | - |
dc.subject.keywordAuthor | 적외선 카메라 | - |
dc.subject.keywordAuthor | 객체 탐지 | - |
dc.subject.keywordAuthor | 인셉션 모듈 | - |
dc.subject.keywordAuthor | 딥러닝 | - |
dc.subject.keywordAuthor | 자율주행차 | - |
dc.subject.keywordAuthor | 생성적 적대 신경망 | - |
dc.subject.keywordAuthor | Data augmentation | - |
dc.subject.keywordAuthor | Infrared camera | - |
dc.subject.keywordAuthor | Object detection | - |
dc.subject.keywordAuthor | Inception module | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Autonomous vehicles | - |
dc.subject.keywordAuthor | Generative adversarial network | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.