DC Field | Value | Language |
---|---|---|
dc.contributor.author | YU, SON CHEOL | - |
dc.contributor.author | MINSUNG, SUNG | - |
dc.date.accessioned | 2018-05-10T06:52:21Z | - |
dc.date.available | 2018-05-10T06:52:21Z | - |
dc.date.created | 2018-02-22 | - |
dc.date.issued | 2017-11-30 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/41686 | - |
dc.description.abstract | CNN composed of 24 convolutional layers and two fully-connected layers. We then trained the CNN with custom fish images. Actual fish images and videos are used to train and evaluate the CNN. The CNN recorded 93% detection accuracy and ran at 16.7 frames per second (FPS). The proposed method can detect fish in dim, noisy, and hazy underwater optical images precisely and accurately in a real time without preprocessing of images | - |
dc.language | Korean | - |
dc.publisher | 한국수중·수상로봇기술연구회 | - |
dc.relation.isPartOf | 2017 한국수중수상로봇기술연구회 추계학술대회 | - |
dc.relation.isPartOf | 2017 한국수중·수상로봇기술연구회 추계학술대회 | - |
dc.title | 뉴럴 네트워크를 이용한 수중 이미지에서의 실시간 물고기 인식 방법 | - |
dc.title.alternative | Vision based Real-time Fish Detection Using Convolutional Neural Network | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | 2017 한국수중수상로봇기술연구회 추계학술대회, pp.1 - 3 | - |
dc.citation.conferenceDate | 2017-11-30 | - |
dc.citation.conferencePlace | KO | - |
dc.citation.conferencePlace | 포항 베스트웨스턴 호텔 | - |
dc.citation.endPage | 3 | - |
dc.citation.startPage | 1 | - |
dc.citation.title | 2017 한국수중수상로봇기술연구회 추계학술대회 | - |
dc.contributor.affiliatedAuthor | YU, SON CHEOL | - |
dc.contributor.affiliatedAuthor | MINSUNG, SUNG | - |
dc.description.journalClass | 2 | - |
dc.description.journalClass | 2 | - |
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.