skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Locally Orderless Tracking

International journal of computer vision, 2015-01, Vol.111 (2), p.213-228 [Peer Reviewed Journal]

Springer Science+Business Media New York 2014 ;COPYRIGHT 2015 Springer ;ISSN: 0920-5691 ;EISSN: 1573-1405 ;DOI: 10.1007/s11263-014-0740-6

Full text available

Citations Cited by
  • Title:
    Locally Orderless Tracking
  • Author: Oron, Shaul ; Bar-Hillel, Aharon ; Levi, Dan ; Avidan, Shai
  • Subjects: Algorithms ; Analysis ; Artificial Intelligence ; Computer Imaging ; Computer Science ; Cost control ; Estimates ; Grounds ; Image Processing and Computer Vision ; Mathematical models ; Noise ; On-line systems ; Pattern Recognition ; Pattern Recognition and Graphics ; State of the art ; Tracking ; Vision
  • Is Part Of: International journal of computer vision, 2015-01, Vol.111 (2), p.213-228
  • Description: Locally Orderless Tracking (LOT) is a visual tracking algorithm that automatically estimates the amount of local (dis)order in the target. This lets the tracker specialize in both rigid and deformable objects on-line and with no prior assumptions. We provide a probabilistic model of the target variations over time. We then rigorously show that this model is a special case of the Earth Mover’s Distance optimization problem where the ground distance is governed by some underlying noise model. This noise model has several parameters that control the cost of moving pixels and changing their color. We develop two such noise models and demonstrate how their parameters can be estimated on-line during tracking to account for the amount of local (dis)order in the target. We also discuss the significance of this on-line parameter update and demonstrate its contribution to the performance. Finally we show LOT’s tracking capabilities on challenging video sequences, both commonly used and new, displaying performance comparable to state-of-the-art methods.
  • Publisher: Boston: Springer US
  • Language: English
  • Identifier: ISSN: 0920-5691
    EISSN: 1573-1405
    DOI: 10.1007/s11263-014-0740-6
  • Source: ProQuest Central

Searching Remote Databases, Please Wait