Show simple item record

dc.contributor.authorHerrero, Nicolasen_US
dc.contributor.authorLandabaso, Jose-Luisen_US
dc.contributor.authorGallego, Guillermoen_US
dc.contributor.authorPujol-Alcolado, Jose-Carlosen_US
dc.date.accessioned2013-09-04T20:36:49Z
dc.date.available2013-09-04T20:36:49Z
dc.date.issued2010-09
dc.identifier.citationHerrero, N.; Landabaso, J.-L.; Gallego, G.; Pujol-Alcolado, J.-C., "In-loop feature tracking for structure and motion with out-of-core optimization," 17th IEEE International Conference on Image Processing (ICIP), 2937-2940, 26-29 Sept. 2010.en_US
dc.identifier.isbn978-1-4244-7992-4
dc.identifier.issn1522-4880
dc.identifier.urihttp://hdl.handle.net/1853/48788
dc.description©2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, 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 components of this work in other works.en_US
dc.descriptionPresented at the 17th IEEE International Conference on Image Processing (ICIP), September 26–29, 2010, Hong Kong.en_US
dc.descriptionDOI: 10.1109/ICIP.2010.5652179en_US
dc.description.abstractIn this paper, a novel and approach for obtaining 3D models from video sequences captured with hand-held cameras is addressed. We define a pipeline that robustly deals with different types of sequences and acquiring devices. Our system follows a divide and conquer approach: after a frame decimation that pre-conditions the input sequence, the video is split into short-length clips. This allows to parallelize the reconstruction step which translates to a reduction in the amount of computational resources required. The short length of the clips allows an intensive search for the best solution at each step of reconstruction which robustifies the system. The process of feature tracking is embedded within the reconstruction loop for each clip as a difference with other approaches. A final registration step, merges all the processed clips to the same coordinate frame.en_US
dc.language.isoen_USen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectGaussian mixture modelen_US
dc.subjectAverage silhouette image representionen_US
dc.subjectDimension reduction algorithmen_US
dc.subjectDistribution parameteren_US
dc.subjectHuman gait recognitionen_US
dc.titleIn-loop feature tracking for structure and motion with out-of-core optimizationen_US
dc.typeProceedingsen_US
dc.typePost-printen_US
dc.contributor.corporatenameTelefonica Researchen_US
dc.contributor.corporatenameGeorgia Institute of Technology. School of Electrical and Computer Engineeringen_US
dc.publisher.originalInstitute of Electrical and Electronics Engineersen_US
dc.identifier.doi10.1109/ICIP.2010.5652179


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record