From lines to Polygons: Polygonal building contour extraction from High-Resolution remote sensing imagery

被引:5
|
作者
Wei, Shiqing [1 ,2 ]
Zhang, Tao [2 ]
Yu, Dawen [2 ]
Ji, Shunping [2 ]
Zhang, Yongjun [2 ]
Gong, Jianya [2 ]
机构
[1] China Univ Petr East China, Coll Oceanog & Space Informat, Qingdao 266580, Peoples R China
[2] Wuhan Univ, Sch Remote Sensing & Informat & Engn, 129 Luoyu Rd, Wuhan 430079, Peoples R China
基金
中国国家自然科学基金;
关键词
Building extraction; Feature line detection; Transformer; Topological reconstruction; Remote sensing images;
D O I
10.1016/j.isprsjprs.2024.02.001
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
Automated extraction of polygonal building contours from high -resolution remote sensing images is important for various applications. However, it remains a difficult task to achieve automated extraction of polygonal buildings at the level of human delineation due to diverse building structures and imperfect image conditions. In this paper, we propose Line2Poly, an end -to -end approach that uses feature lines as geometric primitives to achieve polygonal building extraction by recovering topological relationships among these lines within an individual building. To extract building feature lines with precision, we adopt a two -stage strategy that combines Convolutional Neural Network (CNN) and transformer architectures. A CNN -based module extracts preliminary feature lines, which serve as positional priors for initializing positional queries in the subsequent transformerbased module. For polygonal building contour reconstruction, we devise a learnable polygon topology reconstruction module that predicts adjacency relationships among discrete lines, and integrates lines into building polygons. The resultant building polygons, based on feature lines, exhibit inherent regularity that aligns with manual labeling standards. Extensive experiments on the Vectorizing World Buildings dataset, the WHU aerial building dataset and the WHU-Mix (vector) dataset validate Line2Poly's impressive performance in building feature line extraction and instance -level building detection. Moreover, Line2Poly's predictions exhibit the highest level of concurrence with manual delineations, with over 83% agreement on the WHU aerial building test set and 68.7/59.7% on the WHU-Mix (vector) test set I and II, respectively.
引用
收藏
页码:213 / 232
页数:20
相关论文
共 50 条
  • [41] 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
  • [42] Multitask Learning-based Building Extraction from High-Resolution Remote Sensing Images
    Zhu P.
    Li S.
    Zhang L.
    Li Y.
    Journal of Geo-Information Science, 2021, 23 (03) : 514 - 523
  • [43] Building Extraction from High-Resolution Remote Sensing Image based on Res_AttentionUnet
    Li C.
    Huang F.
    Hu W.
    Zeng J.
    Journal of Geo-Information Science, 2021, 23 (12) : 2232 - 2243
  • [44] Fault-Tolerant Building Change Detection From Urban High-Resolution Remote Sensing Imagery
    Tang, Yuqi
    Huang, Xin
    Zhang, Liangpei
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2013, 10 (05) : 1060 - 1064
  • [45] Urban villages extraction from high-resolution remote sensing imagery based on landscape semantic metrics
    Zhang T.
    Ding L.
    Shi F.
    Cehui Xuebao/Acta Geodaetica et Cartographica Sinica, 2021, 50 (01): : 97 - 104
  • [46] Memory-Contrastive Unsupervised Domain Adaptation for Building Extraction of High-Resolution Remote Sensing Imagery
    Chen, Jie
    He, Peien
    Zhu, Jingru
    Guo, Ya
    Sun, Geng
    Deng, Min
    Li, Haifeng
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [47] 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)
  • [48] A New Building Recognition Algorithm from High Resolution Remote Sensing Imagery
    Chen, Z.
    Wang, G. Y.
    Liu, J. G.
    Cheng, C. J.
    Deng, J. H.
    MIPPR 2011: REMOTE SENSING IMAGE PROCESSING, GEOGRAPHIC INFORMATION SYSTEMS, AND OTHER APPLICATIONS, 2011, 8006
  • [49] Hierarchical Optimization Method of Building Contour in High-Resolution Remote Sensing Images
    Chang Jingxin
    Wang Shuangxi
    Yang Yuanwei
    Gao Xianjun
    CHINESE JOURNAL OF LASERS-ZHONGGUO JIGUANG, 2020, 47 (10):
  • [50] Hierarchical Optimization Method of Building Contour in High-Resolution Remote Sensing Images
    Chang J.
    Wang S.
    Yang Y.
    Gao X.
    Zhongguo Jiguang/Chinese Journal of Lasers, 2020, 47 (10):