Building Multi-Feature Fusion Refined Network for Building Extraction from High-Resolution Remote Sensing Images

被引:23
|
作者
Ran, Shuhao [1 ]
Gao, Xianjun [1 ]
Yang, Yuanwei [1 ,2 ,3 ]
Li, Shaohua [1 ]
Zhang, Guangbin [1 ]
Wang, Ping [4 ,5 ]
机构
[1] Yangtze Univ, Sch Geosci, Wuhan 430100, Peoples R China
[2] Beijing Key Lab Urban Spatial Informat Engn, Beijing 100045, Peoples R China
[3] Hunan Univ Sci & Technol, Hunan Prov Key Lab Geoinformat Engn Surveying Map, Xiangtan 411201, Peoples R China
[4] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China
[5] Key Lab Earth Observat Hainan Prov, Sanya 572029, Peoples R China
基金
中国国家自然科学基金;
关键词
high-resolution remote sensing images; building extraction; multiscale features; aggregate semantic information; feature pyramid; SEMANTIC SEGMENTATION; AERIAL IMAGES; CLASSIFICATION;
D O I
10.3390/rs13142794
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Deep learning approaches have been widely used in building automatic extraction tasks and have made great progress in recent years. However, the missing detection and wrong detection causing by spectrum confusion is still a great challenge. The existing fully convolutional networks (FCNs) cannot effectively distinguish whether the feature differences are from one building or the building and its adjacent non-building objects. In order to overcome the limitations, a building multi-feature fusion refined network (BMFR-Net) was presented in this paper to extract buildings accurately and completely. BMFR-Net is based on an encoding and decoding structure, mainly consisting of two parts: the continuous atrous convolution pyramid (CACP) module and the multiscale output fusion constraint (MOFC) structure. The CACP module is positioned at the end of the contracting path and it effectively minimizes the loss of effective information in multiscale feature extraction and fusion by using parallel continuous small-scale atrous convolution. To improve the ability to aggregate semantic information from the context, the MOFC structure performs predictive output at each stage of the expanding path and integrates the results into the network. Furthermore, the multilevel joint weighted loss function effectively updates parameters well away from the output layer, enhancing the learning capacity of the network for low-level abstract features. The experimental results demonstrate that the proposed BMFR-Net outperforms the other five state-of-the-art approaches in both visual interpretation and quantitative evaluation.
引用
收藏
页数:24
相关论文
共 50 条
  • [21] PANet: Pixelwise Affinity Network for Weakly Supervised Building Extraction From High-Resolution Remote Sensing Images
    Yan, Xin
    Shen, Li
    Wang, Jicheng
    Wang, Yong
    Li, Zhilin
    Xu, Zhu
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [22] Multi-channel recurrent attention network for building extraction from high resolution remote sensing images
    Wang, Zhen
    Xu, Nan
    Wang, Buhong
    Guo, Jianxin
    Zhang, Shanwen
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2022, 33 (05)
  • [23] BRRNet: A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images
    Shao, Zhenfeng
    Tang, Penghao
    Wang, Zhongyuan
    Saleem, Nayyer
    Yam, Sarath
    Sommai, Chatpong
    REMOTE SENSING, 2020, 12 (06)
  • [24] High-Resolution Image Building Extraction Based on Multi-level Feature Fusion Network
    Li X.
    Bai X.
    Li Z.
    Zuo Z.
    Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University, 2022, 47 (08): : 1236 - 1244
  • [25] A Multi-Branch Feature Fusion Network for Building Detection in Remote Sensing Images
    Li, Chao
    Huang, Xinyu
    Tang, Jiechen
    Wang, Kai
    IEEE ACCESS, 2021, 9 (09): : 168511 - 168519
  • [26] MFFNet: A Building Extraction Network for Multi-Source High-Resolution Remote Sensing Data
    Liu, Keliang
    Xi, Yantao
    Liu, Junrong
    Zhou, Wangyan
    Zhang, Yidan
    APPLIED SCIENCES-BASEL, 2023, 13 (24):
  • [27] Feature Residual Analysis Network for Building Extraction from Remote Sensing Images
    Miao, Yuqi
    Jiang, Shanshan
    Xu, Yiming
    Wang, Dongjie
    APPLIED SCIENCES-BASEL, 2022, 12 (10):
  • [28] A Road Extraction Method of a High-Resolution Remote Sensing Image Based on Multi-Feature Fusion and the Attention Mechanism
    Jiang, Na
    Li, Jiyuan
    Yang, Jingyu
    Lin, Junting
    Lu, Baopeng
    TRAITEMENT DU SIGNAL, 2022, 39 (06) : 1907 - 1916
  • [29] Multi-featured multi-scale combination of high-resolution remote sensing images for building extraction
    Niu, Yuhan
    APPLIED MATHEMATICS AND NONLINEAR SCIENCES, 2023, 9 (01)
  • [30] Building Extraction from High-Resolution Remote-Sensing Images Based on Deep Learning
    You, Haihui
    Li, Linhui
    Jing, Weipeng
    ELEKTROTEHNISKI VESTNIK, 2020, 87 (05): : 281 - 286