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

被引:33
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 48 条
[1]   Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks [J].
Alshehhi, Rasha ;
Marpu, Prashanth Reddy ;
Woon, Wei Lee ;
Dalla Mura, Mauro .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2017, 130 :139-149
[2]   SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [J].
Badrinarayanan, Vijay ;
Kendall, Alex ;
Cipolla, Roberto .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) :2481-2495
[3]   Building Footprint Extraction From VHR Remote Sensing Images Combined With Normalized DSMs Using Fused Fully Convolutional Networks [J].
Bittner, Ksenia ;
Adam, Fathalrahman ;
Cui, Shiyong ;
Koerner, Marco ;
Reinartz, Peter .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2018, 11 (08) :2615-2629
[4]   RS-DCNN: A novel distributed convolutional-neural-networks based-approach for big remote-sensing image classification [J].
Boulila, Wadii ;
Sellami, Mokhtar ;
Driss, Maha ;
Al-Sarem, Mohammed ;
Safaei, Mahmood ;
Ghaleb, Fuad A. .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2021, 182
[5]   Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [J].
Chen, Liang-Chieh ;
Zhu, Yukun ;
Papandreou, George ;
Schroff, Florian ;
Adam, Hartwig .
COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 :833-851
[6]   DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [J].
Chen, Liang-Chieh ;
Papandreou, George ;
Kokkinos, Iasonas ;
Murphy, Kevin ;
Yuille, Alan L. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) :834-848
[7]  
Chollet F., KERAS 2 2 4 KERAS 2 2 4
[8]   A tutorial on the cross-entropy method [J].
De Boer, PT ;
Kroese, DP ;
Mannor, S ;
Rubinstein, RY .
ANNALS OF OPERATIONS RESEARCH, 2005, 134 (01) :19-67
[9]   Attention-Gate-Based Encoder-Decoder Network for Automatical Building Extraction [J].
Deng, Wenjing ;
Shi, Qian ;
Li, Jun .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 (14) :2611-2620
[10]   ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data [J].
Diakogiannis, Foivos, I ;
Waldner, Francois ;
Caccetta, Peter ;
Wu, Chen .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2020, 162 (162) :94-114