IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v15y2023i4p3343-d1065495.html
   My bibliography  Save this article

A Light-Weight Neural Network Using Multiscale Hybrid Attention for Building Change Detection

Author

Listed:
  • Zhihua Hua

    (School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454003, China
    MNR Key Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, Henan Polytechnic University, Jiaozuo 454003, China)

  • Haiyang Yu

    (School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454003, China
    MNR Key Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, Henan Polytechnic University, Jiaozuo 454003, China)

  • Peng Jing

    (School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454003, China
    MNR Key Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, Henan Polytechnic University, Jiaozuo 454003, China)

  • Caoyuan Song

    (School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454003, China
    MNR Key Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, Henan Polytechnic University, Jiaozuo 454003, China)

  • Saifei Xie

    (School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454003, China
    MNR Key Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, Henan Polytechnic University, Jiaozuo 454003, China)

Abstract

The study of high-precision building change detection is essential for the sustainable development of land resources. However, remote sensing imaging illumination variation and alignment errors have a large impact on the accuracy of building change detection. A novel lightweight Siamese neural network building change detection model is proposed for the error detection problem caused by non-real changes in high-resolution remote sensing images. The lightweight feature extraction module in the model acquires local contextual information at different scales, allowing it to fully learn local and global features. The hybrid attention module consisting of the channel and spatial attention can make full use of the rich spatiotemporal semantic information around the building to achieve accurate extraction of changing buildings. For the problems of large span of changing building scales, which easily lead to rough extraction of building edge details and missed detection of small-scale buildings, the multi-scale concept is introduced to divide the extracted feature maps into multiple sub-regions and introduce the hybrid attention module separately, and finally, the output features of different scales are weighted and fused to enhance the edge detail extraction capability. The model was experimented on the WHU-CD and LEVIR-CD public data sets and achieved F1 scores of 87.8% and 88.1%, respectively, which have higher change detection accuracy than the six comparison models, and only cost 9.15 G MACs and 3.20 M parameters. The results show that our model can achieve higher accuracy while significantly reducing the number of model parameters.

Suggested Citation

  • Zhihua Hua & Haiyang Yu & Peng Jing & Caoyuan Song & Saifei Xie, 2023. "A Light-Weight Neural Network Using Multiscale Hybrid Attention for Building Change Detection," Sustainability, MDPI, vol. 15(4), pages 1-20, February.
    • Handle: RePEc:gam:jsusta:v:15:y:2023:i:4:p:3343-:d:1065495
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/15/4/3343/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2071-1050/15/4/3343/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Anil Bhujel & Na-Eun Kim & Elanchezhian Arulmozhi & Jayanta Kumar Basak & Hyeon-Tae Kim, 2022. "A Lightweight Attention-Based Convolutional Neural Networks for Tomato Leaf Disease Classification," Agriculture, MDPI, vol. 12(2), pages 1-18, February.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Dudu Guo & Yang Wang & Shunying Zhu & Xin Li, 2023. "A Vehicle Detection Method Based on an Improved U-YOLO Network for High-Resolution Remote-Sensing Images," Sustainability, MDPI, vol. 15(13), pages 1-15, June.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Taejoo Kim & Hyeongjun Kim & Kyeonghoon Baik & Yukyung Choi, 2022. "Instance-Aware Plant Disease Detection by Utilizing Saliency Map and Self-Supervised Pre-Training," Agriculture, MDPI, vol. 12(8), pages 1-16, July.
    2. Yanlei Xu & Shuolin Kong & Zongmei Gao & Qingyuan Chen & Yubin Jiao & Chenxiao Li, 2022. "HLNet Model and Application in Crop Leaf Diseases Identification," Sustainability, MDPI, vol. 14(14), pages 1-20, July.
    3. Xianguo Ren & Haiqing Tian & Kai Zhao & Dapeng Li & Ziqing Xiao & Yang Yu & Fei Liu, 2022. "Research on pH Value Detection Method during Maize Silage Secondary Fermentation Based on Computer Vision," Agriculture, MDPI, vol. 12(10), pages 1-17, October.
    4. Zahid Ullah & Najah Alsubaie & Mona Jamjoom & Samah H. Alajmani & Farrukh Saleem, 2023. "EffiMob-Net: A Deep Learning-Based Hybrid Model for Detection and Identification of Tomato Diseases Using Leaf Images," Agriculture, MDPI, vol. 13(3), pages 1-13, March.
    5. Xiang Zhang & Huiyi Gao & Li Wan, 2022. "Classification of Fine-Grained Crop Disease by Dilated Convolution and Improved Channel Attention Module," Agriculture, MDPI, vol. 12(10), pages 1-16, October.
    6. Dasen Li & Zhendong Yin & Yanlong Zhao & Wudi Zhao & Jiqing Li, 2023. "MLFAnet: A Tomato Disease Classification Method Focusing on OOD Generalization," Agriculture, MDPI, vol. 13(6), pages 1-15, May.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:15:y:2023:i:4:p:3343-:d:1065495. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.