Automatic 2D-to-3D conversion of single low depth-of-field images

Simple item page
dc.contributor.advisorNicolls, Freden_ZA
dc.contributor.authorReddy, Serendraen_ZA
dc.date.accessioned2017-06-06T09:31:08Z
dc.date.available2017-06-06T09:31:08Z
dc.date.issued2017en_ZA
dc.description.abstractThis research presents a novel approach to the automatic rendering of 3D stereoscopic disparity image pairs from single 2D low depth-of-field (LDOF) images. Initially a depth map is produced through the assignment of depth to every delineated object and region in the image. Subsequently the left and right disparity images are produced through depth imagebased rendering (DIBR). The objects and regions in the image are initially assigned to one of six proposed groups or labels. Labelling is performed in two stages. The first involves the delineation of the dominant object-of-interest (OOI). The second involves the global object and region grouping of the non-OOI regions. The matting of the OOI is also performed in two stages. Initially the in focus foreground or region-of-interest (ROI) is separated from the out of focus background. This is achieved through the correlation of edge, gradient and higher-order statistics (HOS) saliencies. Refinement of the ROI is performed using k-means segmentation and CIEDE2000 colour-difference matching. Subsequently the OOI is extracted from within the ROI through analysis of the dominant gradients and edge saliencies together with k-means segmentation. Depth is assigned to each of the six labels by correlating Gestalt-based principles with vanishing point estimation, gradient plane approximation and depth from defocus (DfD). To minimise some of the dis-occlusions that are generated through the 3D warping sub-process within the DIBR process the depth map is pre-smoothed using an asymmetric bilateral filter. Hole-filling of the remaining dis-occlusions is performed through nearest-neighbour horizontal interpolation, which incorporates depth as well as direction of warp. To minimising the effects of the lateral striations, specific directional Gaussian and circular averaging smoothing is applied independently to each view, with additional average filtering applied to the border transitions. Each stage of the proposed model is benchmarked against data from several significant publications. Novel contributions are made in the sub-speciality fields of ROI estimation, OOI matting, LDOF image classification, Gestalt-based region categorisation, vanishing point detection, relative depth assignment and hole-filling or inpainting. An important contribution is made towards the overall knowledge base of automatic 2D-to-3D conversion techniques, through the collation of existing information, expansion of existing methods and development of newer concepts.en_ZA
dc.identifier.apacitationReddy, S. (2017). <i>Automatic 2D-to-3D conversion of single low depth-of-field images</i>. (Thesis). University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering. Retrieved from http://hdl.handle.net/11427/24475en_ZA
dc.identifier.chicagocitationReddy, Serendra. <i>"Automatic 2D-to-3D conversion of single low depth-of-field images."</i> Thesis., University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering, 2017. http://hdl.handle.net/11427/24475en_ZA
dc.identifier.citationReddy, S. 2017. Automatic 2D-to-3D conversion of single low depth-of-field images. University of Cape Town.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Reddy, Serendra AB - This research presents a novel approach to the automatic rendering of 3D stereoscopic disparity image pairs from single 2D low depth-of-field (LDOF) images. Initially a depth map is produced through the assignment of depth to every delineated object and region in the image. Subsequently the left and right disparity images are produced through depth imagebased rendering (DIBR). The objects and regions in the image are initially assigned to one of six proposed groups or labels. Labelling is performed in two stages. The first involves the delineation of the dominant object-of-interest (OOI). The second involves the global object and region grouping of the non-OOI regions. The matting of the OOI is also performed in two stages. Initially the in focus foreground or region-of-interest (ROI) is separated from the out of focus background. This is achieved through the correlation of edge, gradient and higher-order statistics (HOS) saliencies. Refinement of the ROI is performed using k-means segmentation and CIEDE2000 colour-difference matching. Subsequently the OOI is extracted from within the ROI through analysis of the dominant gradients and edge saliencies together with k-means segmentation. Depth is assigned to each of the six labels by correlating Gestalt-based principles with vanishing point estimation, gradient plane approximation and depth from defocus (DfD). To minimise some of the dis-occlusions that are generated through the 3D warping sub-process within the DIBR process the depth map is pre-smoothed using an asymmetric bilateral filter. Hole-filling of the remaining dis-occlusions is performed through nearest-neighbour horizontal interpolation, which incorporates depth as well as direction of warp. To minimising the effects of the lateral striations, specific directional Gaussian and circular averaging smoothing is applied independently to each view, with additional average filtering applied to the border transitions. Each stage of the proposed model is benchmarked against data from several significant publications. Novel contributions are made in the sub-speciality fields of ROI estimation, OOI matting, LDOF image classification, Gestalt-based region categorisation, vanishing point detection, relative depth assignment and hole-filling or inpainting. An important contribution is made towards the overall knowledge base of automatic 2D-to-3D conversion techniques, through the collation of existing information, expansion of existing methods and development of newer concepts. DA - 2017 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2017 T1 - Automatic 2D-to-3D conversion of single low depth-of-field images TI - Automatic 2D-to-3D conversion of single low depth-of-field images UR - http://hdl.handle.net/11427/24475 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/24475
dc.identifier.vancouvercitationReddy S. Automatic 2D-to-3D conversion of single low depth-of-field images. [Thesis]. University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering, 2017 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/24475en_ZA
dc.language.isoengen_ZA
dc.publisher.departmentDepartment of Electrical Engineeringen_ZA
dc.publisher.facultyFaculty of Engineering and the Built Environment
dc.publisher.institutionUniversity of Cape Town
dc.subject.otherElectrical Engineeringen_ZA
dc.titleAutomatic 2D-to-3D conversion of single low depth-of-field imagesen_ZA
dc.typeDoctoral Thesis
dc.type.qualificationlevelDoctoral
dc.type.qualificationnamePhDen_ZA
uct.type.filetypeText
uct.type.filetypeImage
uct.type.publicationResearchen_ZA
uct.type.resourceThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_ebe_2017_reddy_serendra.pdf
Size:
12.78 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
PhD / Doctoral