Show simple item record

Bottom-up Object Segmentation for Visual Recognition

dc.contributor.advisorSminchisescu, Cristian
dc.contributor.authorCarreira, João Luís da Silva
dc.date.accessioned2020-04-18T16:45:59Z
dc.date.available2020-04-18T16:45:59Z
dc.date.issued20.03.2013
dc.identifier.urihttp://hdl.handle.net/20.500.11811/5617
dc.description.abstractAutomatic recognition and segmentation of objects in images is a central open problem in computer vision. Most previous approaches have pursued either sliding-window object detection or dense classification of overlapping local image patches.
Differently, the framework introduced in this thesis attempts to identify the spatial extent of objects prior to recognition, using bottom-up computational processes and mid-level selection cues. After a set of plausible object hypotheses is identified, a sequential recognition process is executed, based on continuous estimates of the spatial overlap between the image segment hypotheses and each putative class.
The object hypotheses are represented as figure-ground segmentations, and are extracted automatically, without prior knowledge of the properties of individual object classes, by solving a sequence of constrained parametric min-cut problems (CPMC) on a regular image grid. It is show that CPMC significantly outperforms the state of the art for low-level segmentation in the PASCAL VOC 2009 and 2010 datasets.
Results beyond the current state of the art for image classification, object detection and semantic segmentation are also demonstrated in a number of challenging datasets including Caltech-101, ETHZ-Shape as well as PASCAL VOC 2009-11. These results suggest that a greater emphasis on grouping and image organization may be valuable for making progress in high-level tasks such as object recognition and scene understanding.
dc.language.isoeng
dc.rightsIn Copyright
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/
dc.subject.ddc004 Informatik
dc.titleBottom-up Object Segmentation for Visual Recognition
dc.typeDissertation oder Habilitation
dc.publisher.nameUniversitäts- und Landesbibliothek Bonn
dc.publisher.locationBonn
dc.rights.accessRightsopenAccess
dc.identifier.urnhttps://nbn-resolving.org/urn:nbn:de:hbz:5n-31098
ulbbn.pubtypeErstveröffentlichung
ulbbnediss.affiliation.nameRheinische Friedrich-Wilhelms-Universität Bonn
ulbbnediss.affiliation.locationBonn
ulbbnediss.thesis.levelDissertation
ulbbnediss.dissID3109
ulbbnediss.date.accepted2012-12-19
ulbbnediss.fakultaetMathematisch-Naturwissenschaftliche Fakultät
dc.contributor.coRefereeKlein, Reinhard


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

The following license files are associated with this item:

InCopyright