Technical Program

Session Detail

Session Title WE2.R4: Deep Learning for Multispectral Image Analysis II
Presentation Mode Oral
Session Time Wednesday, 31 July, 10:40 - 12:20
Location Room 313-314
Session ChairsDevis Tuia, Wageningen and Matthieu Molinier, VTT Technical Research Centre of Finland Ltd

WE2.R4.1: UNSUPERVISED MULTIPLE-CHANGE DETECTION IN VHR MULTISENSOR IMAGES VIA DEEP-LEARNING BASED ADAPTATION
         Sudipan Saha; Fondazione Bruno Kessler
         Francesca Bovolo; Fondazione Bruno Kessler
         Lorenzo Bruzzone; University of Trento

WE2.R4.2: FUSING MULTI-SEASONAL SENTINEL-2 IMAGES WITH RESIDUAL CONVOLUTIONAL NEURAL NETWORKS FOR LOCAL CLIMATE ZONE-DERIVED URBAN LAND COVER CLASSIFICATION
         Chunping Qiu; Technical University of Munich (TUM)
         Michael Schmitt; Technical University of Munich (TUM)
         Xiao Xiang Zhu; Technical University of Munich (TUM)

WE2.R4.3: ROAD MAPPING IN LIDAR IMAGES USING A JOINT-TASK DENSE DILATED CONVOLUTIONS MERGING NETWORK
         Qinghui Liu; Norwegian Computing Center
         Michael Kampffmeyer; Arctic University of Norway
         Robert Jenssen; Arctic University of Norway
         Arnt-Børre Salberg; Norwegian Computing Center

WE2.R4.4: SEMANTIC VEHICLE SEGMENTATION IN VERY HIGH RESOLUTION MULTISPECTRAL AERIAL IMAGES USING DEEP NEURAL NETWORKS
         Nina Merkle; German Aerospace Center (DLR)
         Seyed Majid Azimi; German Aerospace Center (DLR)
         Sebastian Pless; German Aerospace Center (DLR)
         Franz Kurz; German Aerospace Center (DLR)

WE2.R4.5: AVOIDING OVERFITTING WHEN APPLYING SPECTRAL-SPATIAL DEEP LEARNING METHODS ON HYPERSPECTRAL IMAGES WITH LIMITED LABELS
         Matthieu Molinier; VTT Technical Research Centre of Finland Ltd
         Jorma Kilpi; VTT Technical Research Centre of Finland Ltd