Paper Info

Title | ||
---|---|---|

Variational stereo matching with left right consistency constraint |

Abstract | ||
---|---|---|

Variational methods are one of the most useful techniques for stereo matching. Those methods usually take the following pipeline: first, the disparity is embedded in a functional; second, minimizing the functional is converted to solve an Euler-Lagrange(EL) function; third, fix point algorithm or other numerical algorithms are used to solve the EL function in a digital computer. If the functional is not convex, the solution easily bias towards a local minimal solution. Our work in this paper is to alleviate these biases. We model the disparity function in a maximum a posteriori(MAP) continuous Markov random field(MRF) framework and a symmetric functional is then deduced. In such a functional, more constraints can be applied to restrict the solution space. Left-right consistency constraints is introduced as a prior energy in our functional. Experiments on the test images from the Middlebury website show that the proposed functional gives less biases than the previously used one. |

Year | DOI | Venue |
---|---|---|

2011 | 10.1109/SoCPaR.2011.6089110 | SoCPaR |

Keywords | Field | DocType |

left-right consistency constraints,image processing,stereo matching,disparity function,random processes,maximum likelihood estimation,digital computer,numerical analysis,variational method,symmetric functional,fix point algorithm,functional minimization,maximum a posteriori continuous markov random field framework,middlebury web site,numerical algorithm,el function,map continuous mrf framework,stereo image processing,markov processes,euler-lagrange function,variational stereo matching,fixed point,computer vision,mathematical model,stereo vision,optical imaging,pattern recognition,symmetric function | Mathematical optimization,Markov process,Markov random field,Computer science,Variational method,Stereopsis,Image processing,Stochastic process,Artificial intelligence,Maximum a posteriori estimation,Numerical analysis,Machine learning | Conference |

Volume | Issue | ISBN |

null | null | 978-1-4577-1195-4 |

Citations | PageRank | References |

0 | 0.34 | 14 |

Authors | ||

4 |

Authors (4 rows)

Cited by (0 rows)

References (14 rows)

Name | Order | Citations | PageRank |
---|---|---|---|

Wenqiao Zhu | 1 | 0 | 0.34 |

Dongming Lu | 2 | 163 | 32.29 |

Changyu Diao | 3 | 4 | 2.32 |

Jingzhou Huang | 4 | 0 | 0.34 |