Slide Fifth
Slide Second
Slide Fourth
Slide Sixth
Slide Sixth
International Geoscience and Remote Sensing Symposium

In 2021 a joint initiative of Belgium and The Netherlands

WE2.MM-3.4

CASCADED DEEP NEURAL NETWORKS FOR PREDICTING BIASES BETWEEN BUILDING POLYGONS IN VECTOR MAPS AND NEW REMOTE SENSING IMAGES

Mingyang Hu, Wuhan University, China; Meng Lu, Utrecht University, China; Shunping Ji, Wuhan University, China
Session:
Advanced Segmentation for Landcover/Data Fusion
Track:
Data Analysis Methods (Optical, Multispectral,Hyperspectral, SAR)
Presentation Time:
Wed, 14 Jul, 11:15-11:20 (UTC)
Wed, 14 Jul, 13:15-13:20 Central Europe Summer Time (UTC +2)
Wed, 14 Jul, 19:15-19:20 China Standard Time (UTC +8)
Wed, 14 Jul, 07:15-07:20 Eastern Daylight Time (UTC -4)
Session Co-Chairs:
Charles Peureux, Collecte Localisation Satellites and Marian-Daniel Iordache, Flemish Institute for Technological Research, Remote Sensing Department (VITO-TAP)
Session Manager:
Wufan Zhao
Presentation
Not logged in.
Discussion
Not logged in.
Resources
Not logged in.
Session WE2.MM-3
WE2.MM-3.1: A DEEP INTERACTIVE FRAMEWORK FOR BUILDING EXTRACTION IN REMOTELY SENSED IMAGES VIA A COARSE-TO-FINE STRATEGY
Kun Li, Xiangyun Hu, Wuhan University, China
WE2.MM-3.2: CORNER-GUIDED BUILDING POLYGON CONSTRUCTION FROM AERIAL IMAGES USING DEEP MULTITASK LEARNING
Ziming Li, Qinchuan Xin, Sun Yat-Sen University, China
WE2.MM-3.3: ATTENTION RESIDUAL U-NET FOR BUILDING SEGMENTATION IN AERIAL IMAGES
Chaohui Li, Yingjian Liu, Haoyu Yin, Yue Li, Qingxiang Guo, Limin Zhang, Pengting Du, Ocean University of China, China
WE2.MM-3.4: CASCADED DEEP NEURAL NETWORKS FOR PREDICTING BIASES BETWEEN BUILDING POLYGONS IN VECTOR MAPS AND NEW REMOTE SENSING IMAGES
Mingyang Hu, Wuhan University, China; Meng Lu, Utrecht University, China; Shunping Ji, Wuhan University, China
WE2.MM-3.5: DEEP LEARNING BASED WATER SEGMENTATION USING KOMPSAT-5 SAR IMAGES
Myeung Un Kim, Han Oh, Seung-Jae Lee, Yeonju Choi, Sanghyuck Han, Korea Aerospace Research Institute, Korea (South)
WE2.MM-3.6: A NOVEL DEEP TRANSFER LEARNING METHOD FOR SAR AND OPTICAL FUSION IMAGERY SEMANTIC SEGMENTATION
Yanjuan Liu, Yingying Kong, Nanjing University of Aeronautics and Astronautics, China
WE2.MM-3.7: SEA-LAND SEGMENTATION OF REMOTE SENSING IMAGE BASED ON SPATIAL CONSTRAINT MODEL SUPERPIXEL METHOD
JiaLe Zha, Huai-Xin Chen, University of Electronic Science and Technology of China, China; ChengWu Bai, Sichuan Provincial Administration of Production Safety, China; ChengJie Ren, University of Electronic Science and Technology of China, China
WE2.MM-3.8: SEGMENTATION OF SENTINEL-1 SAR IMAGES OVER THE OCEAN, PRELIMINARY METHODS AND ASSESSMENTS
Aurélien Colin, Charles Peureux, Romain Husson, Collecte Localisation Satellites, France; Nicolas Longépé, Φ-lab Explore Office, Italy; Régis Rauzy, Collecte Localisation Satellites, France; Ronan Fablet, Pierre Tandeo, Samir Saoudi, Lab-STICC, UMR CNRS 6285, France; Alexis Mouche, Laboratoire d’Océanographie Physique et Spatiale, France; Gérald Dibarboure, Centre National d’Études Spatiales, France
WE2.MM-3.9: RESIDUAL ATTENTION MECHANISM FOR CONSTRUCTION DISTURBANCE DETECTION FROM SATELLITE IMAGE
Ning Lv, Hao Yuan, Chen Chen, Jiaxuan Deng, Tao Su, Xidian University, China; Yang Zhou, Ministry of Water Resources of China, China; Hua Yang, Northwest University, China
WE2.MM-3.10: CADNET: TOP-DOWN CONTEXTUAL SALIENCY DETECTION NETWORK FOR HIGH SPATIAL RESOLUTION REMOTE SENSING IMAGE SHADOW DETECTION
Yang Yang, Mingqiang Guo, Qiqi Zhu, China University of Geosciences, China

Quicklinks

Downloads

Programme guide