Centre de documentation
scientifique

Discriminative feature learning for unsupervised change detection in heterogeneous images based on a coupled neural network / Wei Zhao in IEEE Transactions on geoscience and remote sensing, vol 55 n° 12 (December 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 12 (December 2017) . - pp 7066 - 7080 Titre : Discriminative feature learning for unsupervised change detection in heterogeneous images based on a coupled neural network Type de document : Article/Communication Auteurs : Wei Zhao, Auteur ; Zhirui Wang, Auteur ; Maoguo Gong, Auteur ; Jia Liu, Auteur Année de publication : 2017 Article en page(s) : pp 7066 - 7080 Note générale : Bibliograpie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse discriminante [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal [Termes IGN] détection de changement Résumé : (Auteur) With the application requirement, the technique for change detection based on heterogeneous remote sensing images is paid more attention. However, detecting changes between two heterogeneous images is challenging as they cannot be compared in low-dimensional space. In this paper, we construct an approximately symmetric deep neural network with two sides containing the same number of coupled layers to transform the two images into the same feature space. The two images are connected with the two sides and transformed into the same feature space, in which their features are more discriminative and the difference image can be generated by comparing paired features pixel by pixel. The network is first built by stacked restricted Boltzmann machines, and then, the parameters are updated in a special way based on clustering. The special way, motivated by that two heterogeneous images share the same reality in unchanged areas and retain respective properties in changed areas, shrinks the distance between paired features transformed from unchanged positions, and enlarges the distance between paired features extracted from changed positions. It is achieved through introducing two types of labels and updating parameters by adaptively changed learning rate. This is different from the existing methods based on deep learning that just do operations on positions predicted to be unchanged and extract only one type of labels. The whole process is completely unsupervised without any priori knowledge. Besides, the method can also be applied to homogeneous images. We test our method on heterogeneous images and homogeneous images. The proposed method achieves quite high accuracy. Numéro de notice : A2017-768 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2739800 En ligne : https://doi.org/10.1109/TGRS.2017.2739800 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88807 [article]