DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Jaeho | ko |
dc.contributor.author | Yoo, Seungwoo | ko |
dc.contributor.author | Kim, Changick | ko |
dc.contributor.author | Vasudev, Bhaskaran | ko |
dc.date.accessioned | 2013-08-08T05:01:13Z | - |
dc.date.available | 2013-08-08T05:01:13Z | - |
dc.date.created | 2013-06-24 | - |
dc.date.created | 2013-06-24 | - |
dc.date.issued | 2013-06 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON BROADCASTING, v.59, no.2, pp.238 - 250 | - |
dc.identifier.issn | 0018-9316 | - |
dc.identifier.uri | http://hdl.handle.net/10203/174351 | - |
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 3-D 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 the human visual system 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. 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 the case of object-view) and by analyzing scene structures (in the 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 effectively be extended to image sequences by employing depth propagation techniques. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | 2D-TO-3D VIDEO CONVERSION | - |
dc.subject | STEREOSCOPIC VIDEO | - |
dc.subject | IMAGE GENERATION | - |
dc.subject | EDGE INFORMATION | - |
dc.subject | 2D | - |
dc.subject | PROPAGATION | - |
dc.subject | SEQUENCE | - |
dc.subject | SHAPE | - |
dc.title | Estimating Scene-Oriented Pseudo Depth With Pictorial Depth Cues | - |
dc.type | Article | - |
dc.identifier.wosid | 000320995700003 | - |
dc.identifier.scopusid | 2-s2.0-84878278975 | - |
dc.type.rims | ART | - |
dc.citation.volume | 59 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 238 | - |
dc.citation.endingpage | 250 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON BROADCASTING | - |
dc.identifier.doi | 10.1109/TBC.2013.2240131 | - |
dc.contributor.localauthor | Kim, Changick | - |
dc.contributor.nonIdAuthor | Lee, Jaeho | - |
dc.contributor.nonIdAuthor | Yoo, Seungwoo | - |
dc.contributor.nonIdAuthor | Vasudev, Bhaskaran | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | 2D-to-3D conversion | - |
dc.subject.keywordAuthor | bilateral filter | - |
dc.subject.keywordAuthor | depth-image-based rendering (DIBR) | - |
dc.subject.keywordAuthor | human visual system (HVS) | - |
dc.subject.keywordAuthor | salient object | - |
dc.subject.keywordAuthor | scene classification | - |
dc.subject.keywordPlus | 2D-TO-3D VIDEO CONVERSION | - |
dc.subject.keywordPlus | STEREOSCOPIC VIDEO | - |
dc.subject.keywordPlus | IMAGE GENERATION | - |
dc.subject.keywordPlus | EDGE INFORMATION | - |
dc.subject.keywordPlus | 2D | - |
dc.subject.keywordPlus | PROPAGATION | - |
dc.subject.keywordPlus | SEQUENCE | - |
dc.subject.keywordPlus | SHAPE | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.