11633

Fast Exact Hyper-Graph Matching with Dynamic Programming for Spatio-Temporal Data

Oya Celiktutan, Christian Wolf, Bulent Sankur, Eric Lombardi
Dept. of Electrical-Electronics Eng., Bogazici University, Istanbul, Turkey
Bogazici University, 2014

@article{cceliktutan2014fast,

   title={Fast Exact Hyper-graph Matching with Dynamic Programming for Spatio-temporal Data},

   author={c{C}}eliktutan, Oya and Wolf, Christian and Sankur, B{"u}lent and Lombardi, Eric},

   journal={Journal of Mathematical Imaging and Vision},

   pages={1–21},

   year={2014},

   publisher={Springer}

}

Download Download (PDF)   View View   Source Source   

1747

views

Graphs and hyper-graphs are frequently used to recognize complex and often non-rigid patterns in computer vision, either through graph matching or point-set matching with graphs. Most formulations resort to the minimization of a difficult energy function containing geometric or structural terms, frequently coupled with data attached terms involving appearance information. Traditional methods solve the minimization problem approximately, for instance re-sorting to spectral techniques. In this paper, we deal with the spatio-temporal data, for a concrete example, human actions in video sequences. In this context, we first make three realistic assumptions: (i) causality of human movements; (ii) sequential nature of human movements; and (iii) one-to-one mapping of time instants. We show that, under these assumptions, the correspondence problem can be decomposed into a set of subproblems such that each subproblem can be solved recursively in terms of the others, and hence an efficient exact minimization algorithm can be derived using dynamic programming approach. Secondly, we propose a special graphical structure which is elongated in time. We argue that, instead of approximately solving the original problem, a solution can be obtained by exactly solving an approximated problem. An exact minimization algorithm is derived for this structure and successfully applied to action recognition in two settings: video data and Kinect coordinate data.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: