Show simple item record



dc.contributor.authorZimmermann, Karel
dc.contributor.authorMatas, Jiří
dc.contributor.authorSvoboda, Tomáš
dc.date.accessioned2012-06-12T11:38:33Z
dc.date.available2012-06-12T11:38:33Z
dc.date.issued2009-04
dc.identifier.citationKarel Zimmermann, Jirí Matas, and Tomáš Svoboda. Tracking by an optimal sequence of linear predictors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(4):677-692, April 2009.cze
dc.identifier.urihttp://hdl.handle.net/10467/9546
dc.description.abstractWe propose a learning approach to tracking explicitly minimizing the computational complexity of the tracking process subject to user-defined probability of failure (loss-of-lock) and precision. The tracker is formed by a Number of Sequences of Learned Linear Predictors (NoSLLiP). Robustness of NoSLLiP is achieved by modeling the object as a collection of local motion predictors - object motion is estimated by the outlier-tolerant RANSAC algorithm from local predictions. Efficiency of the NoSLLiP tracker stems from (i) the simplicity of the local predictors and (ii) from the fact that all design decisions - the number of local predictors used by the tracker, their computational complexity (i.e. the number of observations the prediction is based on), locations as well as the number of RANSAC iterations are all subject to the optimization (learning) process. All time-consuming operations are performed during the learning stage - tracking is reduced to only a few hundreds integer multiplications in each step. On PC with 1timesK8 3200+, a predictor evaluation requires about 30 mus. The proposed approach is verified on publicly-available sequences with approximately 12000 frames with ground-truth. Experiments demonstrates, superiority in frame rates and robustness with respect to the SIFT detector, Lucas-Kanade tracker and other trackers.eng
dc.language.isocescze
dc.publisherIEEEcze
dc.rights© 2009 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.subjectimage processing and computer visioneng
dc.subjectscene analysiseng
dc.subjecttrackingeng
dc.titleTracking by an Optimal Sequence of Linear Predictorscze
dc.typečlánek z elektronického periodikacze
dc.identifier.doi10.1109/TPAMI.2008.119


Files in this item



This item appears in the following Collection(s)

Show simple item record