Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach

Simple item page
dc.contributor.authorZhu, Qihui
dc.contributor.authorWang, Liming
dc.contributor.authorWu, Yang
dc.contributor.authorShi, Jianbo
dc.date2023-05-17T07:09:08.000
dc.date.accessioned2023-05-22T12:49:08Z
dc.date.available2023-05-22T12:49:08Z
dc.date.issued2008-01-01
dc.date.submitted2012-07-11T10:37:51-07:00
dc.description.abstractWe introduce a shape detection framework called Contour Context Selection for detecting objects in cluttered images using only one exemplar. Shape based detection is invariant to changes of object appearance, and can reason with geometrical abstraction of the object. Our approach uses salient contours as integral tokens for shape matching. We seek a maximal, holistic matching of shapes, which checks shape features froma large spatial extent, as well as long-range contextual relationships among object parts. This amounts to finding the correct figure/ ground contour labeling, and optimal correspondences between control points on/around contours. This removes accidental alignments and does not hallucinate objects in background clutter, without negative training examples. We formulate this task as a set-to-set contour matching problem. Naive methods would require searching over ’exponentially’ many figure/ground contour labelings. We simplify this task by encoding the shape descriptor algebraically in a linear form of contour figure/ground variables. This allows us to use the reliable optimization technique of Linear Programming. We demonstrate our approach on the challenging task of detecting bottles, swans and other objects in cluttered images.
dc.description.commentsZhu, Q., Wang, L., Wu, Y., & Shi, J. The 10th European Conference on Computer Vision. 2008. © 2008 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/6580
dc.legacy.articleid1556
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1556&context=cis_papers&unstamped=1
dc.source.issue520
dc.source.journalDepartmental Papers (CIS)
dc.source.statuspublished
dc.subject.otherComputer Sciences
dc.titleContour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach
dc.typePresentation
digcom.identifiercis_papers/520
digcom.identifier.contextkey3074245
digcom.identifier.submissionpathcis_papers/520
digcom.typeconference
dspace.entity.typePublication
relation.isAuthorOfPublication592362dd-550c-4e79-b8c2-62453e4c06f9
relation.isAuthorOfPublication592362dd-550c-4e79-b8c2-62453e4c06f9
relation.isAuthorOfPublication.latestForDiscovery592362dd-550c-4e79-b8c2-62453e4c06f9
upenn.schoolDepartmentCenterDepartmental Papers (CIS)
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
contour_context_final.pdf
Size:
1.64 MB
Format:
Adobe Portable Document Format
Download
Collection
Presentations