DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Chang-Ick | - |
dc.contributor.advisor | 김창익 | - |
dc.contributor.author | Lee, Jae-Ho | - |
dc.contributor.author | 이재호 | - |
dc.date.accessioned | 2015-04-23T06:12:31Z | - |
dc.date.available | 2015-04-23T06:12:31Z | - |
dc.date.issued | 2014 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=568571&flag=dissertation | - |
dc.identifier.uri | http://hdl.handle.net/10203/196535 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 전기및전자공학과, 2014.2, [ vii, 89 p. ] | - |
dc.description.abstract | Estimating depth information from a single image has recently attracted great attention in 3D-TV applications such as 2D-to-3D conversion owing to an insufficient supply of 3D contents. In this paper, we present a new framework for estimating depth from a single image via scene classification techniques. Our goal is to produce "perceptually reasonable" depth for human viewers; we refer to this as "pesudo depth estimation". Since human visual system (HVS) highly relies on structural information and salient objects in understanding scenes, we propose a framework that combines two depth maps; initial pseudo depth map (PDM) and focus depth map (FDM). We use machine learning based scene classification to classify the image into one of two classes, namely object-view and non-object-view. The initial PDM is estimated by segmenting salient objects (in case of object-view) and analyzing scene structure (in case of non-object-view). The focus blur is locally measured to improve the initial PDM. Two depth maps are combined and a simple filtering method is employed to generate the final PDM. Simulation results show that the proposed method outperforms other state-of-the-art approaches for depth estimation in 2D-to-3D conversion both quantitatively and qualitatively. Furthermore, we discuss how the proposed method can be effectively extended to image sequences. | eng |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Human visual system (HVS) | - |
dc.subject | 관심 객체 | - |
dc.subject | 영상 분류 | - |
dc.subject | 깊이 영상 기반 렌더링 | - |
dc.subject | 2차-3차 변환 | - |
dc.subject | 인간 시각 시스템 | - |
dc.subject | 2D-to-3D conversion | - |
dc.subject | depth-image-based rendering (DIBR) | - |
dc.subject | Scene classification | - |
dc.subject | Salient object | - |
dc.title | A method for estimating depth map on a single outdoor image using scene classification and pictorial depth cues | - |
dc.title.alternative | 영상 분류와 사진 깊이 정보에 기반한 단일 실외 영상에서의 깊이 지도 추정 기법 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 568571/325007 | - |
dc.description.department | 한국과학기술원 : 전기및전자공학과, | - |
dc.identifier.uid | 020085396 | - |
dc.contributor.localauthor | Kim, Chang-Ick | - |
dc.contributor.localauthor | 김창익 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.