Show simple item record



dc.contributor.authorObdržálek, Štěpán
dc.contributor.authorPerd’och, Michal
dc.contributor.authorMatas, Jiří
dc.date.accessioned2012-06-12T08:59:00Z
dc.date.available2012-06-12T08:59:00Z
dc.date.issued2008-06
dc.identifier.citationŠtepán Obdrzálek, Michal Perdoch, and Jirí Matas. Dense linear-time correspondences for tracking. In Proceedings of Workshop on Visual Localization for Mobile Platforms held in conjunction with CVPR 2008, page 8, Piscataway, USA, June 2008. IEEE Computer Society, IEEE Computer Society. CD-ROM.cze
dc.identifier.urihttp://hdl.handle.net/10467/9543
dc.description.abstractA novel method is proposed for the problem of frame-to-frame correspondence search in video sequences. The method, based on hashing of low-dimensional image descriptors, establishes dense correspondences and allows large motions. All image pixels are considered for matching, the notion of interest points is reviewed. In our formulation, points of interest are those that can be reliably matched. Their saliency depends on properties of the chosen matching function and on actual image content. Both computational time and memory requirements of the correspondence search are asymptotically linear in the number of image pixels, irrespective of correspondence density and of image content. All steps of the method are simple and allow for a hardware implementation. Functionality is demonstrated on sequences taken from a vehicle moving in an urban environment.eng
dc.language.isocescze
dc.publisherIEEEcze
dc.rights© 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.eng
dc.titleDense Linear-Time Correspondences for Trackingcze
dc.typepříspěvek z konference - elektronickýcze
dc.identifier.doi10.1109/CVPRW.2008.4563130


Files in this item



This item appears in the following Collection(s)

Show simple item record