HD-Net: High-resolution decoupled network for building footprint extraction via deeply supervised body and boundary decomposition

被引:26
|
作者
Li, Yuxuan [1 ,2 ]
Hong, Danfeng [1 ,2 ]
Li, Chenyu [1 ]
Yao, Jing [1 ]
Chanussot, Jocelyn [1 ,3 ]
机构
[1] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China
[2] Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China
[3] Univ Grenoble Alpes, Inria, CNRS, Grenoble INP,LJK, F-38000 Grenoble, France
基金
中国国家自然科学基金;
关键词
Building footprint extraction; Deep supervision; Feature decoupling; High-resolution network; Multi-task learning; Remote sensing; Semantic segmentation; REMOTE-SENSING IMAGES; MAN-MADE OBJECTS; CLASSIFICATION;
D O I
10.1016/j.isprsjprs.2024.01.022
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
The extraction of building footprints, as a highly challenging task in remote sensing (RS) image -based geospatial object detection and recognition, holds significant importance. Due to the strong coupling in RS images between the body and boundary of buildings, the ability of most currently advanced deep learning models in building footprint extraction remains limited, inevitably meeting the extraction performance bottleneck. To this end, we propose a novel High -resolution Decoupled Network, HD -Net for short, for precious building footprint extraction in RS. HD -Net follows the well-known high -resolution network (HRNet) architecture, which can to a great extent alleviate the coupling issues between body and boundary using its multi -scale information interaction in parallel. More specifically, Our HD -Net innovatively designs the multiple stacked multi -scale feature fusion (MFF) modules, where the MFF module is performed by combining the deep supervision technique and a feature decoupling-recoupling (FDR) module. The FDR module adeptly untangles coupled features into two distinct elements: body and boundary, yielding feature maps enriched with semantic information. This configuration facilitates a step -wise refinement of building extraction and boundary predictions, ensuring the overall continuity of buildings and the precision of their boundaries. Experiments conducted on the three widely -used building datasets, i.e., Massachusetts, WHU, and Inria, demonstrate that HD -Net achieves the most competitive results with minimal parameter count. In detail, HD -Net outperforms contour -guided and local structure -aware network (CGSANet) with intersection over union (IoU) improvements of 0.40%, 0.95%, and 0.73% on the mentioned datasets, while CGSANet is the state-of-the-art algorithm using a hybrid loss function and deep supervision strategy. Furthermore, the code of the HD -Net will be made available freely at https://github.com/danfenghong/ISPRS_HD-Net.
引用
收藏
页码:51 / 65
页数:15
相关论文
共 50 条
  • [31] MDBES-Net: Building Extraction From Remote Sensing Images Based on Multiscale Decoupled Body and Edge Supervision Network
    Xu, Shengjun
    Du, Miao
    Meng, Yuebo
    Liu, Guanghui
    Han, Jiuqiang
    Zhan, Bohan
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 519 - 534
  • [32] Context-content collaborative network for building extraction from high-resolution imagery
    Gong, Maoguo
    Liu, Tongfei
    Zhang, Mingyang
    Zhang, Qingfu
    Lu, Di
    Zheng, Hanhong
    Jiang, Fenlong
    KNOWLEDGE-BASED SYSTEMS, 2023, 263
  • [33] Boundary-guided DCNN for building extraction from high-resolution remote sensing images
    Yang, Sihan
    He, Qiang
    Lim, Jae Hak
    Jeon, Gwanggil
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2024, 132 (9-10): : 5171 - 5171
  • [34] Drainage network extraction from a high-resolution DEM using parallel programming in the .NET Framework
    Du, Chao
    Ye, Aizhong
    Gan, Yanjun
    You, Jinjun
    Duan, Qinyun
    Ma, Feng
    Hou, Jingwen
    JOURNAL OF HYDROLOGY, 2017, 555 : 506 - 517
  • [35] House building extraction from high-resolution remote sensing images based on IEU-Net
    Wang Z.
    Zhou Y.
    Wang S.
    Wang F.
    Xu Z.
    National Remote Sensing Bulletin, 2021, 25 (11) : 2245 - 2254
  • [36] ARE-Net: An Improved Interactive Model for Accurate Building Extraction in High-Resolution Remote Sensing Imagery
    Weng, Qian
    Wang, Qin
    Lin, Yifeng
    Lin, Jiawen
    REMOTE SENSING, 2023, 15 (18)
  • [37] High-resolution bearing estimation via UNItary decomposition artificial neural network (UNIDANN)
    Chang, SH
    Lee, TY
    Fang, WH
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1998, E81A (11) : 2455 - 2462
  • [38] MCMCNet: A Semi-Supervised Road Extraction Network for High-Resolution Remote Sensing Images via Multiple Consistency and Multitask Constraints
    Gao, Lipeng
    Zhou, Yiqing
    Tian, Jiangtao
    Cai, Wenjing
    Lv, Zhiyong
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 1
  • [39] Building Footprint Extraction from High Resolution Aerial Images Using Generative Adversarial Network (GAN) Architecture
    Abdollahi, Abolfazl
    Pradhan, Biswajeet
    Gite, Shilpa
    Alamri, Abdullah
    IEEE ACCESS, 2020, 8 (209517-209527) : 209517 - 209527
  • [40] Building footprint extraction using dual-aspect high-resolution synthetic aperture radar images in urban areas
    Zhang, Fengli
    Liu, Lu
    Shao, Yun
    JOURNAL OF APPLIED REMOTE SENSING, 2012, 6