MAP-MRF Cloud Detection Based on PHD Filtering

Author

Addesso, Paolo ; Conte, Roberto ; Longo, Maurizio ; Restaino, Rocco ; Vivone, Gemine

Author_Institution

Dipt. di Ing. Elettron. e Ing. Inf., Univ. of Salerno, Fisciano, Italy

Volume

5

Issue

3

fYear

2012

fDate

6/1/2012 12:00:00 AM

Firstpage

919

Lastpage

929

Abstract

Temporal correlation has been recently taken into consideration to improve the performances of cloud detection algorithms. We exploit this concept within the Maximum A Posteriori Markov Random Field (MAP-MRF) framework by adding a penalty term which is determined according to the history of cloud masses. Multi Target Tracking of clouds is accomplished by methods of FInite Set STatistics (FISST) and several particle-based implementations are compared among them and with other previous methods both on simulated and real data.

Keywords

Markov processes; atmospheric techniques; clouds; correlation methods; geophysical signal processing; random processes; FISST; FInite Set STatistics; MAP-MRF cloud detection; MAP-MRF framework; Maximum A Posteriori Markov Random Field; PHD filtering; cloud detection algorithms; cloud masses; multitarget tracking; particle-based implementations; penalty term; temporal correlation; Bayesian methods; Clouds; Correlation; Estimation; Optical sensors; Remote sensing; Vectors; Cloud masking; MSG SEVIRI; Markov Random Fields (MRF); Maximum A Posteriori estimation (MAP); Multi-Target Tracking (MTT); PHD filters;

fLanguage

English

Journal_Title

Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of

Publisher

ieee

ISSN

1939-1404

Type

jour

DOI

10.1109/JSTARS.2012.2191144

Filename

6189761