Treffer: Advanced Multi-Sensor Optical Remote Sensing for Urban Land Use and Land Cover Classification: Outcome of the 2018 IEEE GRSS Data Fusion Contest

Title:
Advanced Multi-Sensor Optical Remote Sensing for Urban Land Use and Land Cover Classification: Outcome of the 2018 IEEE GRSS Data Fusion Contest
Authors:
Xu, Yonghao, Du, Bo, Zhang, Liangpei, Cerra, Daniele, Pato, Miguel, Carmona, Emiliano, Prasad, Saurabh, Yokoya, Naoto, Hänsch, Ronny, Le Saux, Bertrand
Contributors:
Wuhan University [China], Deutsches Zentrum für Luft- und Raumfahrt [Köln] (DLR), University of Houston, RIKEN Center for Advanced Intelligence Project [Tokyo] (RIKEN AIP), RIKEN - Institute of Physical and Chemical Research [Japon] (RIKEN), Technical University of Berlin / Technische Universität Berlin (TUB), DTIS, ONERA, Université Paris Saclay (COmUE) [Palaiseau], ONERA-Université Paris Saclay (COmUE)
Source:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 12(6):1709-1724
Publisher Information:
CCSD; IEEE, 2019.
Publication Year:
2019
Collection:
collection:ONERA
collection:ONERA-SACLAY
collection:UNIV-PARIS-SACLAY
collection:GS-ENGINEERING
collection:GS-COMPUTER-SCIENCE
collection:COMUE-UPSACLAY
collection:DTIS_ONERA
Subject Terms:
CONVOLUTIONAL NEURAL NETWORKS (CNN), DEEP LEARNING, HYPERSPECTRAL (HS) IMAGING (HSI), IMAGE ANALYSIS AND DATA FUSION, MULTIMODAL, MULTIRESOLUTION, MULTISOURCE, LIDAR, [SPI]Engineering Sciences [physics], [PHYS]Physics [physics]
Original Identifier:
HAL: hal-02875492
Document Type:
Zeitschrift article<br />Journal articles
Language:
English
ISSN:
1939-1404
Relation:
info:eu-repo/semantics/altIdentifier/doi/10.1109/JSTARS.2019.2911113
DOI:
10.1109/JSTARS.2019.2911113
Access URL:
https://hal.science/hal-02875492
https://hal.science/hal-02875492v1/document
https://hal.science/hal-02875492v1/file/DTIS20066.1592579104_postprint.pdf
Rights:
info:eu-repo/semantics/OpenAccess
Accession Number:
edshal.hal.02875492v1
Database:
HAL

Weitere Informationen

This paper presents the scientific outcomes of the 2018 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2018 Contest addressed the problem of urban observation and monitoring with advanced multi-source optical remote sensing (multispectral LiDAR, hyperspec-tral imaging, and very-high-resolution imagery). The competition was based on urban land use and land cover classification aiming to distinguish between very diverse and detailed classes of urban objects, materials, and vegetation. Besides data fusion, it also quantified the respective assets of the novel sensors used to collect the data. Participants proposed elaborate approaches rooted in remote-sensing but also in machine learning and computer vision to make the most of the available data. Winning approaches combine convolutional neural networks with subtle Earth-observation data scientist expertise.