DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Ryu, Jee-Hwan | - |
dc.contributor.advisor | 유지환 | - |
dc.contributor.author | Kim, Jeongyun | - |
dc.date.accessioned | 2023-06-21T19:30:49Z | - |
dc.date.available | 2023-06-21T19:30:49Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1008124&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/307495 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 건설및환경공학과, 2022.8,[iv, 32 p. :] | - |
dc.description.abstract | Depth information used in SLAM and visual odometry is essential in robotics. Depth information often obtained from sensors or learned by networks. While learning-based methods have gained popularity, they are mostly limited to RGB images. However, the limitation of RGB images occurs in visually derailed environments. Thermal cameras are in the spotlight as a way to solve these problems. Unlike RGB images, thermal images reliably perceive the environment regardless of the illumination variance but show lacking contrast and texture. This low contrast in the thermal image prohibits an algorithm from effectively learning the underlying scene details. To tackle these challenges, we propose multichannel remapping for contrast. My method allows a learning-based depth prediction model to have an accurate depth prediction even in low light conditions. We validate the feasibility and show that my multi-channel remapping method outperforms the existing methods both visually and quantitatively over STheReO dataset. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 열화상카메라▼a컴퓨터 비전▼a머신러닝 | - |
dc.subject | Thermal camera▼acomputer vision▼amachine learning | - |
dc.title | Enhancing single thermal image depth estimation via N-channel remapping for thermal images | - |
dc.title.alternative | 열화상 이미지에 대한 다중 채널 재매핑을 통한 단일 열화상 깊이 추정 향상 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :건설및환경공학과, | - |
dc.contributor.alternativeauthor | 김정윤 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.