Technical Program

Session Detail

Session Title FRP1.PJ: Image Segmentation II
Presentation Mode Poster
Session Time Friday, 02 August, 09:40 - 10:40
Location Room 501-502: Poster Area J
Session ChairsBegüm Demir, Technische Universität Berlin and Naoto Yokoya, RIKEN

FRP1.PJ.1: DEEP LEARNING MODEL FOR WATER/ICE/LAND CLASSIFICATION USING LARGE-SCALE MEDIUM RESOLUTION SATELLITE IMAGES
         Vinayaraj Poliyapram; AIST-Tokyo Tech Real World Big-Data Computation Open Innovation Laboratory (RWBC-OIL)
         Nevrez Imamoglu; National Institute of Advanced Industrial and Science and Technology (AIST)
         Ryousuke Nakamura; National Institute of Advanced Industrial and Science and Technology (AIST)

FRP1.PJ.2: A LEVEL SET BASED METHOD FOR LAND MASKING IN SHIP DETECTION USING SAR IMAGES
         Ziwei Wang; Beihang University
         Wei Yang; Beihang University
         Jie Chen; Beihang University
         Chunsheng Li; Beihang University

FRP1.PJ.3: A DEEP LEARNING FOREST TYPES CLASSIFICATION METHOD FOR HIGH SPATIAL RESOLUTION REMOTE SENSING IMAGE: DUAL-FCN8S-CRF
         Ying Guo; Chinese Academy of Forestry
         Zengyuan Li; Chinese Academy of Forestry
         Erxue Chen; Chinese Academy of Forestry
         Xu Zhang; Chinese Academy of Forestry
         Lei Zhao; Chinese Academy of Forestry
         Yan Chen; Chinese Academy of Forestry
         Yahui Wang; Chinese Academy of Forestry

FRP1.PJ.4: OPTICAL REMOTE SENSING WATER-LAND SEGMENTATION REPRESENTATION BASED ON PROPOSED SNS-CNN NETWORK
         Shan Dong; Communication University of China
         Long Pang; Communication University of China
         Yin Zhuang; Peking University
         Wenchao Liu; Beijing Institute of Technology
         Zhanxin Yang; Communication University of China
         Teng Long; Beijing Institute of Technology

FRP1.PJ.5: SEA-LAND SEGMENTATION FOR HARBOUR IMAGES WITH SUPERPIXEL CRF
         Bin Sun; Hunan University
         Shutao Li; Hunan University
         Jie Xie; Hunan University

FRP1.PJ.6: TRAINING A SINGLE MULTI-CLASS CONVOLUTIONAL SEGMENTATION NETWORK USING MULTIPLE DATASETS WITH HETEROGENEOUS LABELS: PRELIMINARY RESULTS
         Fanjie Kong; Duke University
         Cheng Chen; Duke University
         Bohao Huang; Duke University
         Leslie Collins; Duke University
         Kyle Bradbury; Energy Initiative, Duke University
         Jordan Malof; Duke University

FRP1.PJ.7: A REVERSIBLE GENERATIVE ADVERSARIAL NETWORKS FOR SAR IMAGERY CLUTTER SUPPRESSION
         Qian Zhang; University of Electronic Science and Technology of China
         Li Zheng; University of Electronic Science and Technology of China
         Yulin Huang; University of Electronic Science and Technology of China
         Yin Zhang; University of Electronic Science and Technology of China
         Jianyu Yang; University of Electronic Science and Technology of China
         Junjie Wu; University of Electronic Science and Technology of China
         Haiguang Yang; University of Electronic Science and Technology of China

FRP1.PJ.8: EFFECTIVE FUSION OF MULTI-MODAL DATA WITH GROUP CONVOLUTIONS FOR SEMANTIC SEGMENTATION OF AERIAL IMAGERY
         Kaiqiang Chen; University of Chinese Academy of Sciences
         Kun Fu; Chinese Academy of Sciences
         Xin Gao; Chinese Academy of Sciences
         Menglong Yan; Chinese Academy of Sciences
         Wenkai Zhang; Chinese Academy of Sciences
         Yue Zhang; Chinese Academy of Sciences
         Xian Sun; Chinese Academy of Sciences

FRP1.PJ.9: APPLICATION OF UNET FULLY CONVOLUTIONAL NEURAL NETWORK TO IMPERVIOUS SURFACE SEGMENTATION IN URBAN ENVIRONMENT FROM HIGH RESOLUTION SATELLITE IMAGERY
         Joe McGlinchy; University of Colorado Boulder
         Brian Johnson; University of Colorado Boulder
         Brian Muller; University of Colorado Boulder
         Maxwell Joseph; University of Colorado Boulder
         Jeremy Diaz; University of Colorado Boulder

FRP1.PJ.10: AN AUTOMATIC LAND COVERS IDENTIFICATION BASED ON DEMPSTER-SHAFER THEORY FOR MULTI-SPECTRAL IMAGES
         Na Li; University of Rennes 1 - TOTAL
         Arnaud Martin; University of Rennes 1
         Remi Estival; Total