Segmentation-based extraction of important objects from video for object-based indexing

Simple item page
buir.contributor.authorGüdükbay, Uğur
dc.citation.epage1360en_US
dc.citation.spage1357en_US
dc.contributor.authorBaştan, Muhammeten_US
dc.contributor.authorGüdükbay, Uğuren_US
dc.contributor.authorUlusoy, Özgüren_US
dc.coverage.spatialHannover, Germany
dc.date.accessioned2016-02-08T11:37:38Z
dc.date.available2016-02-08T11:37:38Z
dc.date.issued2008-06en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionDate of Conference: 23-26 June, 2008
dc.descriptionConference name: IEEE International Conference on Multimedia and Expo, 2008
dc.description.abstractWe describe a method to automatically extract important video objects for object-based indexing. Most of the existing salient object detection approaches detect visually conspicuous structures in images, while our method aims to find regions that may be important for indexing in a video database system. Our method works on a shot basis. We first segment each frame to obtain homogeneous regions in terms of color and texture. Then, we extract a set of regional and inter-regional color, shape, texture and motion features for all regions, which are classified as being important or not using SVMs trained on a few hundreds of example regions. Finally, each important region is tracked within each shot for trajectory generation and consistency check. Experimental results from news video sequences show that the proposed approach is effective. © 2008 IEEE.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T11:37:38Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2008en
dc.identifier.doi10.1109/ICME.2008.4607695en_US
dc.identifier.urihttp://hdl.handle.net/11693/26852
dc.language.isoEnglishen_US
dc.publisherIEEE
dc.relation.isversionofhttp://dx.doi.org/10.1109/ICME.2008.4607695en_US
dc.source.titleIEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedingsen_US
dc.subjectImportant objecten_US
dc.subjectIndexingen_US
dc.subjectSegmentationen_US
dc.subjectVideo object extractionen_US
dc.subjectDatabase systemsen_US
dc.subjectExhibitionsen_US
dc.subjectFeature extractionen_US
dc.subjectIndexing (of information)en_US
dc.subjectMotion compensationen_US
dc.subjectMotion estimationen_US
dc.subjectPhotographyen_US
dc.subjectTexturesen_US
dc.subjectVideo recordingen_US
dc.subjectConsistency checksen_US
dc.subjectHomogeneous regionsen_US
dc.subjectImportant objecten_US
dc.subjectMotion featuresen_US
dc.subjectNews videosen_US
dc.subjectSalient object detectionsen_US
dc.subjectSegmentationen_US
dc.subjectTrajectory generationsen_US
dc.subjectVideo database systemsen_US
dc.subjectVideo object extractionen_US
dc.subjectVideo objectsen_US
dc.subjectObject recognitionen_US
dc.titleSegmentation-based extraction of important objects from video for object-based indexingen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Segmentation-based extraction of important objects from video for object-based indexing.pdf
Size:
402.91 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Computer Engineering