SPATIAL RELATIONAL REASONING IN NETWORKS FOR IMPROVING SEMANTIC SEGMENTATION OF AERIAL IMAGES

被引:0
作者
Mou, Lichao [1 ,2 ]
Hua, Yuansheng [1 ,2 ]
Zhu, Xiao Xiang [1 ,2 ]
机构
[1] German Aerosp Ctr DLR, Remote Sensing Technol Inst IMF, Cologne, Germany
[2] TUM, Signal Proc Earth Observat SiPEO, Munich, Germany
来源
2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019) | 2019年
关键词
Relation network; fully convolutional network; semantic segmentation; aerial imagery;
D O I
10.1109/igarss.2019.8900224
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Most current semantic segmentation approaches rely on deep convolutional neural networks (CNNs). However, their use of convolution operations with local receptive fields causes failures in modeling contextual spatial relations. Prior works have tried to address this issue by using graphical models or spatial propagation modules in networks. But such models often fail to capture long-range spatial relationships between entities, which leads to spatially fragmented predictions. In this work, we introduce a simple yet effective network unit, the spatial relation module, to learn and reason about global relationships between any two spatial positions, and then produce relation-enhanced feature representations. The spatial relation module is general and extensible, and can be used in a plug-and-play fashion with the existing fully convolutional network (FCN) framework. We evaluate spatial relation module-equipped networks on semantic segmentation tasks using two aerial image datasets. The networks achieve very competitive results, bringing significant improvements over baselines.
引用
收藏
页码:5232 / 5235
页数:4
相关论文
共 50 条
[41]   Adaptive Boundary and Semantic Composite Segmentation Method for Individual Objects in Aerial Images [J].
Li, Ying ;
Gong, Guanghong ;
Wang, Dan ;
Li, Ni .
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES, 2023, 136 (03) :2237-2265
[42]   Artificial intelligence based semantic segmentation on aerial images with variational mode decomposition [J].
Vijai, Anupa ;
Padmavathi, S. ;
Venkataraman, D. .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 156
[43]   PROTOTYPE-BASED CLUSTERED FEDERATED LEARNING FOR SEMANTIC SEGMENTATION OF AERIAL IMAGES [J].
Zhang, Boning ;
Zhang, Xiaokang ;
Pun, Man-On ;
Liu, Ming .
2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, :2227-2230
[44]   YUTO SEMANTIC: A LARGE SCALE AERIAL LIDAR DATASET FOR SEMANTIC SEGMENTATION [J].
Yoo, S. ;
Ko, C. ;
Sohn, G. ;
Lee, H. .
GEOSPATIAL WEEK 2023, VOL. 48-1, 2023, :209-215
[45]   Dual-Stream Feature Aggregation Network for Unmanned Aerial Vehicle Aerial Images Semantic Segmentation [J].
Li Runzeng ;
Shi Zaifeng ;
Kong Fanning ;
Zhao Xiangyang ;
Luo Tao .
LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (24)
[46]   HECR-Net: Height-Embedding Context Reassembly Network for Semantic Segmentation in Aerial Images [J].
Liu, Wenjie ;
Zhang, Wenkai ;
Sun, Xian ;
Guo, Zhi ;
Fu, Kun .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 (14) :9117-9131
[47]   Semantic Segmentation of Vineyard Images Using Convolutional Neural Networks [J].
Kalampokas, Theofanis ;
Tziridis, Konstantinos ;
Nikolaou, Alexandros ;
Vrochidou, Eleni ;
Papakostas, George A. ;
Pachidis, Theodore ;
Kaburlasos, Vassilis G. .
PROCEEDINGS OF THE 21ST ENGINEERING APPLICATIONS OF NEURAL NETWORKS CONFERENCE, EANN 2020, 2020, 2 :292-303
[48]   Semantic Segmentation of Histopathological Images with Fully and Dilated Convolutional Networks [J].
Turhan, Huseyin ;
Bilgin, Gokhan .
TIP TEKNOLOJILERI KONGRESI (TIPTEKNO'21), 2021,
[49]   Improving Semantic Segmentation of 3D Medical Images on 3D Convolutional Neural Networks [J].
Marquez Herrera, Alejandra ;
Cuadros-Vargas, Alex J. ;
Pedrini, Helio .
2019 XLV LATIN AMERICAN COMPUTING CONFERENCE (CLEI 2019), 2019,
[50]   Power Line Segmentation in Aerial Images Using Convolutional Neural Networks [J].
Saurav, Sumeet ;
Gidde, Prashant ;
Singh, Sanjay ;
Saini, Ravi .
PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PREMI 2019, PT I, 2019, 11941 :623-632