Scheda di dettaglio – i prodotti della ricerca
| Dato | Valore |
|---|---|
| Title | A new supervised classifier exploiting spectral-spatial information in the Bayesian framework |
| Abstract | Conventional machine learning methods are often unable to achieve high degrees of accuracy when only spectral data are involved in the classification process. The main reason of that inaccuracy can be brought back to the omission of the spatial information in the classification. The present paper suggests a way to combine effectively the spectral and the spatial information and improve the classification's accuracy. In practice, a Bayesian two-stage methodology is proposed embodying two enhancements: i) a geostatistical non-parametric classification approach, the universal indicator kriging and the smooth multivariate kernel method. The former provides an informative prior, while the latter overcomes the assumption (often not true) of independence of the spectral data. The case study reports an application to land-cover classification in a study area located in the Apulia region (Southern Italy). The methodology performance in terms of overall accuracy was compared with five state-of-the-art methods, i.e. naive Bayes, Random Forest, artificial neural networks, support vector machines and decision trees. It is shown that the proposed methodology outperforms all the compared methods and that even a severe reduction of the training set does not affect seriously the average accuracy of the presented method. |
| Source | International journal of applied earth observation and geoinformation 86 |
| Keywords | Land-cover classificationBayes' methodmultivariate smooth kerneluniversal indicator kriging |
| Journal | International journal of applied earth observation and geoinformation |
| Editor | International Institute for Aerial Survey and Earth Sciences, Enschede, |
| Year | 2019 |
| Type | Articolo in rivista |
| DOI | 10.1016/j.jag.2019.101990 |
| Authors | Barca, Emanuele; Castrignano, Annamaria; Ruggieri, Sergio; Rinaldi, Michele |
| Text | 424060 2019 10.1016/j.jag.2019.101990 ISI Web of Science WOS 000509787800006 Scopus 2 s2.0 85086763263 Land cover classification Bayes method multivariate smooth kernel universal indicator kriging A new supervised classifier exploiting spectral spatial information in the Bayesian framework Barca, Emanuele; Castrignano, Annamaria; Ruggieri, Sergio; Rinaldi, Michele Italian Res Council IRSA CNR; Council Agr Res Econ; Council Agr Res Econ Conventional machine learning methods are often unable to achieve high degrees of accuracy when only spectral data are involved in the classification process. The main reason of that inaccuracy can be brought back to the omission of the spatial information in the classification. The present paper suggests a way to combine effectively the spectral and the spatial information and improve the classification s accuracy. In practice, a Bayesian two stage methodology is proposed embodying two enhancements i a geostatistical non parametric classification approach, the universal indicator kriging and the smooth multivariate kernel method. The former provides an informative prior, while the latter overcomes the assumption often not true of independence of the spectral data. The case study reports an application to land cover classification in a study area located in the Apulia region Southern Italy . The methodology performance in terms of overall accuracy was compared with five state of the art methods, i.e. naive Bayes, Random Forest, artificial neural networks, support vector machines and decision trees. It is shown that the proposed methodology outperforms all the compared methods and that even a severe reduction of the training set does not affect seriously the average accuracy of the presented method. 86 Published version https //www.sciencedirect.com/science/article/pii/S0303243418310638 A new supervised classifier exploiting spectral spatial information in the Bayesian framework 01.pdf Articolo in rivista International Institute for Aerial Survey and Earth Sciences 1569 8432 International journal of applied earth observation and geoinformation International journal of applied earth observation and geoinformation Int. j. appl. earth obs. geoinf. International journal of applied earth observation and geoinformation. JAG ITC journal emanuele.barca BARCA EMANUELE |