Message Board

Respected readers, authors and reviewers, you can add comments to this page on any questions about the contribution, review,        editing and publication of this journal. We will give you an answer as soon as possible. Thank you for your support!

Name
E-mail
Phone
Title
Content
Verification Code
Turn off MathJax
Article Contents

GAO Xianjun, RAN Shuhao, ZHANG Guangbin, YANG Yuanwei. Building Extraction Based on Multi-feature Fusion and Object-boundary Joint Constraint Network[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210520
Citation: GAO Xianjun, RAN Shuhao, ZHANG Guangbin, YANG Yuanwei. Building Extraction Based on Multi-feature Fusion and Object-boundary Joint Constraint Network[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210520

Building Extraction Based on Multi-feature Fusion and Object-boundary Joint Constraint Network

doi: 10.13203/j.whugis20210520
Funds:

The Open Fund of Beijing Key Laboratory of Urban Spatial Information Engineering (No.20210205)

  • Received Date: 2022-06-20
  • Objectives: Accurately and automatically extracting buildings from high-resolution remote sensing images is of great significance in many aspects, such as urban planning, map data updating, emergency response, etc.The problems of missing and wrong detection of buildings and missing boundaries caused by spectrum confusion still exist in the existing full convolution neural networks (FCN). Methods: In order to overcome the limitations, a multi-feature fusion and object-boundary joint constraint network was presented in this paper. The method is based on an encoding and decoding structure. In the encoding stage, the continuous-atrous spatial pyramid module (CSPM) is positioned at the end to extract and combine multi-scale features without sacrificing too much useful information. In the decoding stage, more accurate building features are integrated into the network and the boundary is refined, by implementing the multi-output fusion constraint structure (MFCS) based on object and boundary. In the skip connection between the encoding and decoding stages, the convolutional block attention module (CBAM) is introduced to enhance the effective features. Furthermore, the multi-level output results from the decoding stage are used to build a piecewise multi-scale weighted loss function for fine network parameter updating. Results: Comparative experimental analysis was performed on the WHU and Massachusetts building datasets. The results show that:(1) The buildings extraction results proposed by the proposed method are closer to the ground truth. (2) The quantitative evaluation result is higher than the other five state-of-the-art approaches. Specifically, IoU and F1-Score on Massachusetts and WHU building datasets reached 90.44%, 94.98%, and 72.57%, 84.10%, respectively. (3) The proposed model outperforms the MFCNN and BRRNet in both complexity and efficiency. Conclusions: The proposed method not only improves the accuracy and integrity of extraction results in spectral obfuscation buildings, but also maintains a good boundary. It has strong scale robustness.
  • [1] Long J, Shelhamer E, Darrell T.Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston, MA, USA.:3431-3440
    [2] Szegedy C, Liu W, Jia Y Q, et al.Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston, MA.:1-9
    [3] Zhao H S, Shi J P, Qi X J, et al.Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu, HI, USA.:6230-6239
    [4] Chen L C, Papandreou G, Kokkinos I, et al.DeepLab:Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFS[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4):834-848
    [5] Chen L C, Papandreou G, Schroff F, et al.Rethinking Atrous Convolution for Semantic Image Segmentation[EB/OL].2017:arXiv:1706.05587.https://arxiv.org/abs/1706.05587
    [6] Badrinarayanan V, Kendall A, Cipolla R.SegNet:A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12):2481-2495
    [7] Ronneberger O, Fischer P, Brox T.U-Net:Convolutional Networks for Biomedical Image Segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI, Munich, Germany, 2015
    [8] Diakogiannis F I, Waldner F, Caccetta P, et al.ResUNet-A[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 162:94-114
    [9] Shao Z F, Tang P H, Wang Z Y, et al.BRRNet:A Fully Convolutional Neural Network for Automatic Building Extraction from High-Resolution Remote Sensing Images[J].Remote Sensing, 2020, 12(6):1050
    [10] Wei S Q, Ji S P, Lu M.Toward Automatic Building Footprint Delineation from Aerial Images Using CNN and Regularization[J].IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(3):2178-2189
    [11] Xie Y K, Zhu J, Cao Y G, et al.Refined Extraction of Building Outlines from High-Resolution Remote Sensing Imagery Based on a Multifeature Convolutional Neural Network and Morphological Filtering[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13:1842-1855
    [12] Woo S, Park J, Lee J Y, et al.CBAM:Convolutional Block Attention Module[EB/OL].2018:arXiv:1807.06521.https://arxiv.org/abs/1807.06521
    [13] Wang P Q, Chen P F, Yuan Y, et al.Understanding convolution for semantic segmentation[C]//2018 IEEE Winter Conference on Applications of Computer Vision.Lake Tahoe, NV, USA.:1451-1460
    [14] Fu J, Liu J, Tian H J, et al.Dual attention network for scene segmentation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach, CA, USA.:3141-3149
    [15] Lin T Y, Dollár P, Girshick R, et al.Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu, HI, USA.:936-944
    [16] Milletari F, Navab N, Ahmadi S A.V-net:Fully convolutional neural networks for volumetric medical image segmentation[C]//2016 Fourth International Conference on 3D Vision (3DV).Stanford, CA, USA.:565-571
    [17] He S, Jiang W S.Boundary-Assisted Learning for Building Extraction from Optical Remote Sensing Imagery[J].Remote Sensing, 2021, 13(4):760
    [18] Mnih V.Machine Learning for Aerial Image Labeling[D].Toronto:University of Toronto, 2013
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article Metrics

Article views(64) PDF downloads(9) Cited by()

Related
Proportional views

Building Extraction Based on Multi-feature Fusion and Object-boundary Joint Constraint Network

doi: 10.13203/j.whugis20210520
Funds:

The Open Fund of Beijing Key Laboratory of Urban Spatial Information Engineering (No.20210205)

Abstract: Objectives: Accurately and automatically extracting buildings from high-resolution remote sensing images is of great significance in many aspects, such as urban planning, map data updating, emergency response, etc.The problems of missing and wrong detection of buildings and missing boundaries caused by spectrum confusion still exist in the existing full convolution neural networks (FCN). Methods: In order to overcome the limitations, a multi-feature fusion and object-boundary joint constraint network was presented in this paper. The method is based on an encoding and decoding structure. In the encoding stage, the continuous-atrous spatial pyramid module (CSPM) is positioned at the end to extract and combine multi-scale features without sacrificing too much useful information. In the decoding stage, more accurate building features are integrated into the network and the boundary is refined, by implementing the multi-output fusion constraint structure (MFCS) based on object and boundary. In the skip connection between the encoding and decoding stages, the convolutional block attention module (CBAM) is introduced to enhance the effective features. Furthermore, the multi-level output results from the decoding stage are used to build a piecewise multi-scale weighted loss function for fine network parameter updating. Results: Comparative experimental analysis was performed on the WHU and Massachusetts building datasets. The results show that:(1) The buildings extraction results proposed by the proposed method are closer to the ground truth. (2) The quantitative evaluation result is higher than the other five state-of-the-art approaches. Specifically, IoU and F1-Score on Massachusetts and WHU building datasets reached 90.44%, 94.98%, and 72.57%, 84.10%, respectively. (3) The proposed model outperforms the MFCNN and BRRNet in both complexity and efficiency. Conclusions: The proposed method not only improves the accuracy and integrity of extraction results in spectral obfuscation buildings, but also maintains a good boundary. It has strong scale robustness.

GAO Xianjun, RAN Shuhao, ZHANG Guangbin, YANG Yuanwei. Building Extraction Based on Multi-feature Fusion and Object-boundary Joint Constraint Network[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210520
Citation: GAO Xianjun, RAN Shuhao, ZHANG Guangbin, YANG Yuanwei. Building Extraction Based on Multi-feature Fusion and Object-boundary Joint Constraint Network[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210520
Reference (18)

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return