DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yoon, Kuk-Jin | - |
dc.contributor.advisor | 윤국진 | - |
dc.contributor.author | Ryu, Kwonyoung | - |
dc.date.accessioned | 2022-04-15T07:57:49Z | - |
dc.date.available | 2022-04-15T07:57:49Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=949065&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295038 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 기계공학과, 2021.2,[iii, 36 p. :] | - |
dc.description.abstract | Most existing deep learning-based depth completion methods are only suitable for high (\eg 64-scanline) resolution LiDAR measurements, and they usually fail to predict a reliable dense depth map with low resolution (4, 8, or 16-scanline) LiDAR. However, it is of great interest to reduce the number of LiDAR channels in many aspects (cost, weight of a device, power consumption). In this paper, I propose a new depth completion framework with various LiDAR scanline resolutions, which performs as well as methods built for 64-scanline resolution LiDAR inputs. For this, I define a consistency loss between the predictions from LiDAR measurements of different scanline resolutions. (i.e. 4, 8, 16, 32-scanline LiDAR measurements) Also, I design a fusion module to integrate features from different modalities. Experiments show our proposed method outperforms the current state-of-the-art depth completion methods for input LiDAR measurements of low scanline resolution and performs comparably to the methods(models) for input LiDAR measurements of 64-scanline resolution on the KITTI benchmark dataset. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Depth Completion▼aDepth Estimation▼aLiDAR▼aSensor Fusion▼aDeep-learning based method▼aConsistent learning | - |
dc.subject | 영상 깊이 완성▼a영상 깊이 추정▼a라이다▼a센서 정보 융합▼a딥러닝 기반 추정▼a일관성 학습 | - |
dc.title | Scanline resolution-invariant depth completion using a single image and sparse LiDAR point cloud | - |
dc.title.alternative | 단일 이미지와 LiDAR 점구름을 이용한 LiDAR-채널 해상도에 불변한 깊이추정방법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :기계공학과, | - |
dc.contributor.alternativeauthor | 류권영 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.