DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Shin, Jinwoo | - |
dc.contributor.advisor | 신진우 | - |
dc.contributor.author | Imran, Saad | - |
dc.date.accessioned | 2021-05-13T19:39:50Z | - |
dc.date.available | 2021-05-13T19:39:50Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=925246&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/285082 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.8,[iii, 33 p. :] | - |
dc.description.abstract | Unsupervised deep learning methods have shown promising performance for single-image depth estimation. Since most of these methods use binocular stereo pairs for self-supervision, the depth range is generally limited. Small-baseline stereo pairs provide small depth range but handle occlusions well. On the other hand, stereo images acquired with a wide-baseline rig cause occlusions-related errors in the near range but estimate depth well in the far range. In this work, we propose to integrate the advantages of the small and wide baselines. By training the network using three horizontally aligned views, we obtain accurate depth predictions for both close and far ranges. Our strategy allows to infer multi-baseline depth from a single image. This is unlike previous multi-baseline systems which employ more than two cameras. The qualitative and quantitative results show the superior performance of multi-baseline approach over previous stereo-based monocular methods. For 0.1 to 80 meters depth range, our approach decreases the absolute relative error of depth by 24% compared to Monodepth2. Our approach provides 21 frames per second on a single Nvidia1080 GPU, making it useful for practical applications. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Depth Estimation▼aUnsupervised Learning▼aSmall-Baseline▼aWide-Baseline▼aMulti-Baseline | - |
dc.subject | 깊이 평가▼a비지도 학습▼a작은 기준선▼a넓은 기준선▼a다중 기준선 | - |
dc.title | Increased-range unsupervised monocular depth estimation | - |
dc.title.alternative | 단안 카메라를 이용한 깊이 정보 측정 범위의 개선을 위한 비지도학습 기법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 임란 사드 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.