Interpretable Hyperspectral Artificial Intelligence: When nonconvex modeling meets hyperspectral remote sensing
Year: 2021
Type: article
Abstract: Hyperspectral (HS) imaging, also known as image spectrometry, is a landmark technique in geoscience and remote sensing (RS). In the past decade, enormous efforts have been made to process and analyze these HS products, mainly by seasoned experts. However, with an ever-growing volume of data, the bulk of costs in manpower and material resources poses new challenges for reducing the burden of manual labor and improving efficiency. For this reason, it is urgent that more intelligent and automatic approaches for various HS RS applications be developed. Machine learning (ML) tools with convex optimization have successfully undertaken the tasks of numerous artificial intelligence (AI)-related applications; however, their ability to handle complex practical problems remains limited, particularly for HS data, due to the effects of various spectral variabilities in the process of HS imaging and the complexity and redundancy of higher-dimensional HS signals. Compared to convex models, nonconvex modeling, which is capable of characterizing more complex real scenes and providing model interpretability technically and theoretically, has proven to be a feasible solution that reduces the gap between challenging HS vision tasks and currently advanced intelligent data processing models.
Authors: Danfeng Hong, Wei He, Naoto Yokoya, Jing Yao, Lianru Gao, Liangpei Zhang, Jocelyn Chanussot, Xiaoxiang Zhu
Institutions: Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR), RIKEN, RIKEN Center for Advanced Intelligence Project, Xi'an Jiaotong University, Chinese Academy of Sciences, Aerospace Information Research Institute, Wuhan University, State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Institut polytechnique de Grenoble, GIPSA-Lab
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: Purdue University, Deutsche Forschungsgemeinschaft, Agence Nationale de la Recherche, National Natural Science Foundation of China, AXA Research Fund, Bundesministerium für Bildung und Forschung, Università degli Studi di Pavia, Helmholtz Artificial Intelligence Cooperation Unit, Japan Society for the Promotion of Science
Awards: MIAI @ Grenoble Alpes, G3584013848, Development of intelligent earth observation system based on incomplete data reconstruction and automatic selection of training samples, G6064428495, Generative Adversarial Networks Based Multi-Sensor Remote Sensing Image Translation for Disaster Damage Mapping, G7451273612, G7901184878, G8166215770, G8744309892
OpenAlex ID: W3133902755
