DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Soo Hyun | - |
dc.contributor.advisor | 김수현 | - |
dc.contributor.author | Bangunharcana, Antyanta | - |
dc.date.accessioned | 2021-05-11T19:31:03Z | - |
dc.date.available | 2021-05-11T19:31:03Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=875163&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/282915 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 기계공학과, 2019.8,[iv, 48 p. :] | - |
dc.description.abstract | Most of the recent 3D object detection algorithms are based on LiDAR point cloud and algorithms based on images still lacks behind in performance. This is mostly attributed to the less accurate depth estimation from images compared to LiDAR. However, LiDAR are expensive sensors and cameras offers a more efficient alternative if we can construct a reliable algorithm. In this study, we investigate a novel 3D object detection algorithm that utilizes stereo images. The algorithm makes detection on the disparity space images constructed from stereo matching. The features of the images in the disparity space are already computed during the stereo matching algorithm. This way, we expand the detection space from 2D image to 2.5D space while sharing computation with stereo matching algorithm to keep computation cost lower. For that, we also built a memory efficient stereo matching algorithm by modifying the cost volume construction step of existing algorithm. Our stereo matching algorithm is shown to be faster and memory efficient compared to previous methods. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Stereo vision▼adisparity▼acorrelation▼aobject detection▼akeypoint▼aheatmap▼amulti-task CNN | - |
dc.subject | 스테레오 비전▼a불일치▼a상호관계▼a물체인식▼a키포인트▼a히트맵▼a다중처리 합성공 신경망 | - |
dc.title | 3D object detection in disparity space using context guided stereo matching | - |
dc.title.alternative | 컨텍스트 가이드 스테레오 매칭을 이용한 변위 공간에서의 3 차원 물체 검출 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :기계공학과, | - |
dc.contributor.alternativeauthor | 방운할차나 안탼타 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.