Building façade semantic segmentation based on K-means classification and graph analysis

  • Bo MaoEmail author
  • Bingchan Li
Original Paper


Building façade segmentation is essential for smart city-related applications such as energy consumption simulation or urban planning. In this paper, we take advantage of the horizontal self-similarity feature of building texture and propose a building façade segmentation algorithm based on K-means classification. First, the building texture images are rectified to orthogonal projection. Then, texture pixels in each horizontal line are classified into line segments using the K-means method based on CIE color distance. Next, a graph is generated where the nodes represent line segments, and the edges are relatedly connected with color distance attribute of its two nodes. The connected nodes (neighbor line segments) with similar color are aggregated based on which the building main structures such as floors and tiles are detected. The novelty of the proposed method is that the K-means classification is applied to the building texture pixels in a horizontal line that can improve the classification accuracy and increase speed. According to the experimental results, the proposed algorithm can achieve over 90% accuracy on the test dataset compared with traditional methods.


Building texture Semantic segmentation K-means Graph analysis 


Funding information

This research was funded by the National Natural Science Foundation of China (41671457) and the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province (16KJA170003).


  1. Azhar S (2011) Building information modeling (BIM) trends, benefits, risks, and challenges for the AEC industry. Leadersh Manag Eng, Issue 11:3CrossRefGoogle Scholar
  2. Chaudhury K, DiVerdi S, Ioffe S (2014) Auto-rectification of user photos. 2014 IEEE International Conference on Image Processing (ICIP). IEEEGoogle Scholar
  3. Fathalla R, Vogiatzis G (2017) A deep learning pipeline for semantic facade segmentation. In: Proceedings of the British Machine Vision Conference 2016, BMVC 2017, September, 2017. British machine vision conference, 10/09/17Google Scholar
  4. Hassanzadeh A, Kaarna A, Kauranne T (2018) Sequential spectral clustering of hyperspectral remote sensing image over bipartite graph. Appl Soft Comput 73:727–734CrossRefGoogle Scholar
  5. Lian Y, Shen X (2015) Detecting repetitive elements with accurate locations and shapes from urban façade. 2015 IEEE International Conference on Image Processing (ICIP), Quebec City, QC, pp 1920–1924Google Scholar
  6. Liu H, Zhang J, Zhu J, Hoi S (2017) DeepFacade: a deep learning approach to facade parsing. Proceedings of the twenty-sixth international joint conference on artificial intelligence (IJCAI-17) 2301–2307Google Scholar
  7. Mathias M, Martinović A, Van Gool L (2016) ATLAS: a three-layered approach to facade parsing. Int J Comput Vis 118:22–48CrossRefGoogle Scholar
  8. Medeiros RS, Wong A, Scharcanski J (2018) Scalable image segmentation via decoupled sub-graph compression. Pattern Recogn 78:228–241CrossRefGoogle Scholar
  9. Oskouie P, Becerik-Gerber B, Soibelman L (2017) Automated recognition of building açades for creation of as-is mock-up 3D models. J Comput Civ Eng 31:04017059. CrossRefGoogle Scholar
  10. Shao Y, Sang N, Gao C, Ma L (2018) Spatial and class structure regularized sparse representation graph for semi-supervised hyperspectral image classification. Pattern Recogn 81:81–94CrossRefGoogle Scholar
  11. Teboul O, Kokkinos I, Simon L, Koutsourakis P, Paragios N (July 2013) Parsing facades with shape grammars and reinforcement learning. IEEE Trans Pattern Anal Mach Intell 35(7):1744–1756CrossRefGoogle Scholar
  12. Teeravech K, Nagai M, Honda K, Dailey M (2014) Discovering repetitive patterns in facade images using a RANSAC-style algorithm. ISPRS J Photogramm Remote Sens 92:38–53CrossRefGoogle Scholar
  13. Tyleček R, Šára R (2013) Spatial pattern templates for recognition of objects with regular structure. In: Weickert J, Hein M, Schiele B (eds) Pattern recognition. GCPR 2013. Lecture notes in computer science, vol 8142. Springer, BerlinGoogle Scholar
  14. Wang J, Liu C, Shen T, Quan L (2015) Structure-driven facade parsing with irregular patterns. 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), Kuala Lumpur, pp 041–045Google Scholar
  15. Xiao H, Meng G, Wang L, Pan C (2018) Facade repetition detection in a fronto-parallel view with fiducial lines extraction. Neurocomputing 273:435–447CrossRefGoogle Scholar
  16. Yuan H, Li J, Lai LL, Tang YY (2018) Graph-based multiple rank regression for image classification. Neurocomputing 315:394–404CrossRefGoogle Scholar
  17. Zheng Q, Warner S, Tasian G, Fan Y (2018a) A dynamic graph cuts method with integrated multiple feature maps for segmenting kidneys in 2D ultrasound images. Acad Radiol 25(9):1136–1145CrossRefGoogle Scholar
  18. Zheng Q, Li H, Fan B, Wu S, Xu J (2018b) Integrating support vector machine and graph cuts for medical image segmentation. J Vis Commun Image Represent 55:157–165CrossRefGoogle Scholar

Copyright information

© Saudi Society for Geosciences 2019

Authors and Affiliations

  1. 1.College of Information Engineering, Collaborative Innovation Center for Modern Grain Circulation and Safety, Jiangsu Key Laboratory of Grain Big-data MiningNanjing University of Finance & EconomicsNanjingChina
  2. 2.College of Electrical Engineering and AutomationJiangsu Maritime InstituteNanjingChina

Personalised recommendations