DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nam, Hyeonseob | ko |
dc.contributor.author | Hong, Seunghoon | ko |
dc.contributor.author | Han, Bohyung | ko |
dc.date.accessioned | 2019-12-13T13:27:34Z | - |
dc.date.available | 2019-12-13T13:27:34Z | - |
dc.date.created | 2019-11-05 | - |
dc.date.issued | 2014-09-06 | - |
dc.identifier.citation | 13th European Conference on Computer Vision, ECCV 2014, pp.112 - 126 | - |
dc.identifier.uri | http://hdl.handle.net/10203/269672 | - |
dc.description.abstract | Tracking by sequential Bayesian filtering relies on a graphical model with temporally ordered linear structure based on temporal smoothness assumption. This framework is convenient to propagate the posterior through the first-order Markov chain. However, density propagation from a single immediately preceding frame may be unreliable especially in challenging situations such as abrupt appearance changes, fast motion, occlusion, and so on. We propose a visual tracking algorithm based on more general graphical models, where multiple previous frames contribute to computing the posterior in the current frame and edges between frames are created upon inter-frame trackability. Such data-driven graphical model reflects sequence structures as well as target characteristics, and is more desirable to implement a robust tracking algorithm. The proposed tracking algorithm runs online and achieves outstanding performance with respect to the state-of-the-art trackers. We illustrate quantitative and qualitative performance of our algorithm in all the sequences in tracking benchmark and other challenging videos. © 2014 Springer International Publishing. | - |
dc.language | English | - |
dc.publisher | European Conference on Computer Vision Committee | - |
dc.title | Online graph-based tracking | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 112 | - |
dc.citation.endingpage | 126 | - |
dc.citation.publicationname | 13th European Conference on Computer Vision, ECCV 2014 | - |
dc.identifier.conferencecountry | SZ | - |
dc.identifier.conferencelocation | Zurich | - |
dc.identifier.doi | 10.1007/978-3-319-10602-1_8 | - |
dc.contributor.nonIdAuthor | Nam, Hyeonseob | - |
dc.contributor.nonIdAuthor | Han, Bohyung | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.