Centre de documentation
scientifique

Random-walker-based collaborative learning for hyperspectral image classification / Bin Sun in IEEE Transactions on geoscience and remote sensing, vol 55 n° 1 (January 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 1 (January 2017) . - pp 212 - 222 Titre : Random-walker-based collaborative learning for hyperspectral image classification Type de document : Article/Communication Auteurs : Bin Sun, Auteur ; Xudong Kang, Auteur ; Shutao Li, Auteur ; Jon Atli Benediktsson, Auteur Année de publication : 2017 Article en page(s) : pp 212 - 222 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage semi-dirigé [Termes IGN] champ aléatoire de Markov [Termes IGN] classification [Termes IGN] image hyperspectrale Résumé : (Auteur) Active learning (AL) and semisupervised learning (SSL) are both promising solutions to hyperspectral image classification. Given a few initial labeled samples, this work combines AL and SSL in a novel manner, aiming to obtain more manually labeled and pseudolabeled samples and use them together with the initial labeled samples to improve the classification performance. First, based on a comparison of the segmentation and spectral-spatial classification results obtained by random walker (RW) and extended RW (ERW) algorithms, the unlabeled samples are separated into two different sets, i.e., low- and high-confidence unlabeled data sets. For the high-confidence unlabeled data, pseudolabeling is performed, which can ensure the correctness and informativeness of the pseudolabeled samples. For the low-confidence unlabeled data, AL is used to select samples. In this way, the samples which are more effective for improvement of classification performance can be labeled in only a few iterations. Finally, with the learned training set and the original hyperspectral image as inputs, the ERW classifier is used to obtain the final classification result. Experiments performed on three real hyperspectral data sets show that the proposed method can achieve competitive classification accuracy even with a very limited number of manually labeled samples. Numéro de notice : A2017-019 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2604290 En ligne : https://doi.org/10.1109/TGRS.2016.2604290 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83950 [article]