Journal
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
Volume 150, Issue -, Pages 259-273Publisher
ELSEVIER
DOI: 10.1016/j.isprsjprs.2019.02.010
Keywords
Building pattern classification; Graph convolutional neural network; Machine learning; Spatial vector data; Graph Fourier transform; Deep learning
Categories
Funding
- National Key Research and Development Program of China [2017YFB0503500]
- National Natural Science Foundation of China [41531180]
Ask authors/readers for more resources
Machine learning methods, specifically, convolutional neural networks (CNNs), have emerged as an integral part of scientific research in many disciplines. However, these powerful methods often fail to perform pattern analysis and knowledge mining with spatial vector data because in most cases, such data are not underlying grid-like or array structures but can only be modeled as graph structures. The present study introduces a novel graph convolution by converting it from the vertex domain into a point-wise product in the Fourier domain using the graph Fourier transform and convolution theorem. In addition, the graph convolutional neural network (GCNN) architecture is proposed to analyze graph-structured spatial vector data. The focus of this study is the classical task of building pattern classification, which remains limited by the use of design rules and manually extracted features for specific patterns. The spatial vector data representing grouped buildings are modeled as graphs, and indices for the characteristics of individual buildings are investigated to collect the input variables. The pattern features of these graphs are directly extracted by training labeled data. Experiments confirmed that the GCNN produces satisfactory results in terms of identifying regular and irregular patterns, and thus achieves a significant improvement over existing methods. In summary, the GCNN has considerable potential for the analysis of graph structured spatial vector data as well as scope for further improvement.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available