Sökning: WFRF:(He Xiaoxiang)
> (2020-2024) >
Interpretable Hyper...
Interpretable Hyperspectral Artificial Intelligence : When nonconvex modeling meets hyperspectral remote sensing
-
- Hong, Danfeng (författare)
- German Aerosp Ctr DLR, Remote Sensing Technol Inst IMF, Oberpfaffenhofen, Germany.;IMF DLR, Spectral Vis Working Grp, Oberpfaffenhofen, Germany.;Univ Grenoble Alpes, French Natl Ctr Sci Res, Grenoble Inst Technol, GIPSA Lab, F-38000 Grenoble, France.
-
- He, Wei (författare)
- RIKEN, Ctr Adv Intelligence Project, Tokyo 1030027, Japan.
-
- Yokoya, Naoto (författare)
- Univ Tokyo, Tokyo 1030027, Japan.;RIKEN, Ctr Adv Intelligence Project, Geoinformat Unit, Tokyo 1030027, Japan.;German Aerosp Ctr, Oberpfaffenhofen, Germany.;Tech Univ Munich, Munich, Germany.
-
visa fler...
-
- Yao, Jing (författare)
- Tech Univ Munich, Munich, Germany.;Chinese Acad Sci, Key Lab Digital Earth Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China.;German Aerosp Ctr, Remote Sensing Technol Inst, Oberpfaffenhofen, Germany.
-
- Gao, Lianru (författare)
- Chinese Acad Sci, Key Lab Digital Earth Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China.;Univ Extremadura, Caceres, Spain.;Mississippi State Univ, Starkville, MS USA.
-
- Zhang, Liangpei (författare)
- Wuhan Univ, Minist Educ China, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430072, Peoples R China.;China State Key Basic Res Project, Beijing, Peoples R China.;Minist Natl Sci & Technol China, Remote Sensing Program China, Beijing, Peoples R China.
-
- Chanussot, Jocelyn (författare)
- Grenoble INP, Grenoble, France.;Univ Iceland, Reykjavik, Iceland.;Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China.;Stanford Univ, Stanford, CA 94305 USA.;Royal Inst Technol, Stockholm, Sweden.;Natl Univ Singapore, Singapore, Singapore.;Univ Calif Los Angeles, Los Angeles, CA USA.
-
- Zhu, Xiaoxiang (författare)
- Univ Tokyo, Tokyo 1030027, Japan.;Univ Calif Los Angeles, Los Angeles, CA USA.;TUM, Data Sci Earth Observat EO, Munich, Germany.;German Aerosp Ctr DLR, Remote Sensing Technol Inst, Signal Proc EO, Oberpfaffenhofen, Germany.;German Aerosp Ctr DLR, Remote Sensing Technol Inst, EO Data Sci Dept, Oberpfaffenhofen, Germany.;Munich Data Sci Res Sch, Munich, Germany.;Helmholtz Artificial Intelligence Res Field Aeron, Wessling, Germany.;Int Future Artificial Intelligence Lab Artificial, D-80333 Munich, Germany.;TUM, Munich Data Sci Inst, D-80333 Munich, Germany.;Italian Natl Res Council, Naples, Italy.;Fudan Univ, Shanghai, Peoples R China.;Berlin Brandenburg Acad Sci & Humanities, Junges Kolleg, Young Acad, Berlin, Germany.;German Natl Acad Sci Leopoldina, Halle, Germany.;Bavarian Acad Sci & Humanities, Munich, Germany.
-
visa färre...
-
German Aerosp Ctr DLR, Remote Sensing Technol Inst IMF, Oberpfaffenhofen, Germany;IMF DLR, Spectral Vis Working Grp, Oberpfaffenhofen, Germany.;Univ Grenoble Alpes, French Natl Ctr Sci Res, Grenoble Inst Technol, GIPSA Lab, F-38000 Grenoble, France. RIKEN, Ctr Adv Intelligence Project, Tokyo 1030027, Japan. (creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2021
- 2021
- Engelska.
-
Ingår i: IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE. - : Institute of Electrical and Electronics Engineers (IEEE). - 2473-2397. ; 9:2, s. 52-87
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Imaging
- Artificial intelligence
- Data models
- Analytical models
- Two dimensional displays
- Task analysis
- Earth
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas