Paper Info

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

Unsupervised Post-Nonlinear Unmixing of Hyperspectral Images Using a Hamiltonian Monte Carlo Algorithm |

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

This paper presents a nonlinear mixing model for hyperspectral image unmixing. The proposed model assumes that the pixel reflectances are post-nonlinear functions of unknown pure spectral components contaminated by an additive white Gaussian noise. These nonlinear functions are approximated using second-order polynomials leading to a polynomial post-nonlinear mixing model. A Bayesian algorithm is proposed to estimate the parameters involved in the model yielding an unsupervised nonlinear unmixing algorithm. Due to the large number of parameters to be estimated, an efficient Hamiltonian Monte Carlo algorithm is investigated. The classical leapfrog steps of this algorithm are modified to handle the parameter constraints. The performance of the unmixing strategy, including convergence and parameter tuning, is first evaluated on synthetic data. Simulations conducted with real data finally show the accuracy of the proposed unmixing strategy for the analysis of hyperspectral images. |

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

2014 | 10.1109/TIP.2014.2314022 | IEEE Transactions on Image Processing |

Keywords | Field | DocType |

AWGN,Bayes methods,Monte Carlo methods,hyperspectral imaging,image processing,mixture models,nonlinear functions,polynomials,Bayesian algorithm,Hamiltonian Monte Carlo algorithm,additive white Gaussian noise,classical leapfrog steps,hyperspectral images,parameter tuning,pixel reflectances,polynomial post-nonlinear mixing model,post-nonlinear functions,second-order polynomials,synthetic data,unsupervised post-nonlinear unmixing,Hamiltonian Monte Carlo,Hyperspectral imagery,post-nonlinear model,unsupervised spectral unmixing | Approximation algorithm,Computer vision,Monte Carlo method,Nonlinear system,Polynomial,Hybrid Monte Carlo,Algorithm,Hyperspectral imaging,Synthetic data,Artificial intelligence,Additive white Gaussian noise,Mathematics | Journal |

Volume | Issue | ISSN |

23 | 6 | 1057-7149 |

Citations | PageRank | References |

36 | 1.26 | 21 |

Authors | ||

3 |

Authors (3 rows)

Cited by (36 rows)

References (21 rows)

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

Yoann Altmann | 1 | 229 | 22.58 |

Nicolas Dobigeon | 2 | 2070 | 108.02 |

Jean-Yves Tourneret | 3 | 835 | 64.32 |