Centre de documentation
scientifique

Hyperspectral band selection from statistical wavelet models / Siwei Feng in IEEE Transactions on geoscience and remote sensing, vol 55 n° 4 (April 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 4 (April 2017) . - pp 2111 - 2123 Titre : Hyperspectral band selection from statistical wavelet models Type de document : Article/Communication Auteurs : Siwei Feng, Auteur ; Yuki Itoh, Auteur ; Mario Parente, Auteur ; Marco F. Duarte, Auteur Année de publication : 2017 Article en page(s) : pp 2111 - 2123 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] chaîne de Markov [Termes IGN] classification dirigée [Termes IGN] classification spectrale [Termes IGN] image à haute résolution [Termes IGN] image hyperspectrale [Termes IGN] pouvoir de résolution spectrale [Termes IGN] redondance de données [Termes IGN] signature spectrale Résumé : (Auteur) High spectral resolution brings hyperspectral images with large amounts of information, which makes these images more useful in many applications than images obtained from traditional multispectral scanners with low spectral resolution. However, the high data dimensionality of hyperspectral images increases the burden on data computation, storage, and transmission; fortunately, the high redundancy in the spectral domain allows for significant dimensionality reduction. Band selection provides a simple dimensionality reduction scheme by discarding bands that are highly redundant, thereby preserving the structure of the data set. This paper proposes a new criterion for pointwise-ranking-based band selection that uses a nonhomogeneous hidden Markov chain (NHMC) model for redundant wavelet coefficients of each hyperspectral signature. The model provides a binary multiscale label that encodes semantic features that are useful to discriminate spectral types. A band ranking score considers the average correlation among the average NHMC labels for each band. We also test richer discrete-valued label vectors that provide a more finely grained quantization of spectral fluctuations. In addition, since band selection methods based on band ranking often ignore correlations in selected bands, we study the effect of redundancy elimination, applied on the selected features, on the performance of an example classification problem. Our experimental results also include an optional redundancy elimination step and test their effect on classification performance that is based on the selected bands. The experimental results also include a comparison with several relevant supervised band selection techniques. Numéro de notice : A2017-172 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2636850 En ligne : https://doi.org/10.1109/TGRS.2016.2636850 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84717 [article]