View Selection Strategies for Multi-View, Wide-Baseline Stereo

Simple item page
dc.contributor.authorFarid, Hany
dc.contributor.authorLee, Sang Wook
dc.contributor.authorBajcsy, Ruzena
dc.date2023-05-17T01:15:13.000
dc.date.accessioned2023-05-22T12:57:21Z
dc.date.available2023-05-22T12:57:21Z
dc.date.issued1994-05-01
dc.date.submitted2007-08-21T08:16:17-07:00
dc.description.abstractRecovering 3D depth information from two or more 2D intensity images is a long standing problem in the computer vision community. This paper presents a multi-baseline, coarse-to-fine stereo algorithm which utilizes any number of images (more than 2) and multiple image scales to recover 3D depth information. Several "view-selection strategies" are introduced for combining information across the multi-baseline and across scale space. The control strategies allow us to exploit, maximally, the benefits of large and small baselines and mask sizes while minimizing errors. Results of recovering 3D depth information from a human head are presented. The resulting depth maps are of good accuracy with a depth resolution of approximately 5mm.
dc.description.commentsUniversity of Pennsylvania Department of Computer and Information Science Technical Report No. MS-CIS-94-18.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/7467
dc.legacy.articleid1547
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1547&context=cis_reports&unstamped=1
dc.source.issue529
dc.source.journalTechnical Reports (CIS)
dc.source.statuspublished
dc.subject.otherGRASP
dc.titleView Selection Strategies for Multi-View, Wide-Baseline Stereo
dc.typeReport
digcom.contributor.authorFarid, Hany
digcom.contributor.authorLee, Sang Wook
digcom.contributor.authorBajcsy, Ruzena
digcom.identifiercis_reports/529
digcom.identifier.contextkey346656
digcom.identifier.submissionpathcis_reports/529
digcom.typereport
dspace.entity.typePublication
upenn.schoolDepartmentCenterTechnical Reports (CIS)
upenn.schoolDepartmentCenterGeneral Robotics, Automation, Sensing and Perception Laboratory
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
94_18.pdf
Size:
7.13 MB
Format:
Adobe Portable Document Format
Download
Collection
Reports