Recognition of building group patterns using graph convolutional network. Issue 5 (2nd September 2020)

• Record Type: Journal Article
• Authors: Zhao, Rong; Ai, Tinghua; Yu, Wenhao; He, Yakun; Shen, Yilang
• Is Part Of: Cartography and geographic information science. Volume 47:Issue 5(2020)
• Page Start: 400
• Page End: 417
• Publication Date: 2020-09-02
• Subjects: Building groups -- pattern recognition -- convolutional neural networks -- graph convolution -- generalization of buildings; Cartography -- Periodicals; Geographic information systems -- Periodicals; 526
• DOI: 10.1080/15230406.2020.1757512
• Languages: English
• ISSNs: 1523-0406

Abstract

ABSTRACT: Recognition of building group patterns is of great significance for understanding and modeling the urban space. However, many current methods cannot fully utilize spatial information and have trouble efficiently dealing with topographic data with high complexity. The design of intelligent computational models that can act directly on topographic data to extract spatial features is critical. To this end, we propose a novel deep neural network based on graph convolutions to automatically identify building group patterns with arbitrary forms. The method first models buildings by a general graph, and then the neural network simultaneously learns the structural information as well as vertex attributes to classify building objects. We apply this method to real building data, and the experimental results show that the proposed method can effectively capture spatial information to make more accurate predictions than traditional methods.