Journal of Mountain Science

, Volume 15, Issue 7, pp 1460–1470 | Cite as

An improved Mahalanobis distance-based colour segmentation method for rural building recognition

  • Jia-li XieEmail author
  • Yong-shu Li
  • Guo-lin CaiEmail author
  • Feng Wang
  • He-chao Li


Aiming at the rapid identification of rural buildings in complex environments from high-spatialresolution images, an improved Mahalanobis distance colour segmentation method (IMDCSM) is proposed and realised in Red, Green and Blue (RGB) space. Vector sets of a lower discrete degree are obtained by filtering the colour vector sets of the building samples, and a standard ellipsoid equation can be constructed based on these vector sets. The threshold of interested colour range can be flexibly and intuitively selected by changing the shape and size of this ellipsoid. Then, according to the relationship between the location of the image pixel colour vector and the ellipsoid, all building information can be extracted quickly. To verify the effectiveness of the proposed method, unmanned aerial vehicle (UAV) images of two areas in the suburbs of Chengdu city and Deyang city were utilised as experimental data for image segmentation, and the existing colour segmentation method based on the Mahalanobis distance was selected as an indicator to assess the effectiveness of this method. The experimental results demonstrate that the completeness and correctness of this method reached 95% and 83.0%, respectively, values that are higher than those of the Mahalanobis distance colour segmentation method (MDCSM). In general, this method is suitable for the rapid extraction of rural building information, and provides a new threshold selection method for classification.


Mahalanobis distance Red Green and Blue vector Colour image segmentation Rural buildings recognition 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



This work was supported by National Science and Technology Support Project of the 12th Five-Year Plan of China (Grant No.2014BAL01B04), and Sichuan Provincial Department of Land and Resources Research Project (Grant No.KJ-2018-13). The authors are grateful to the editor and reviewers for their constructive comments that have helped improve this work significantly.


  1. Cao HR, Zhang BL (2015) An improved definition of Mahalanobis distance with singular covariance matrix. Mathenatics in Practice and Theory (01): 226–230. (In Chinese)Google Scholar
  2. Cui SY, Yan Q, Reinartz P (2012) Complex building description and extraction based on Hough transformation and cycle detection. Remote Sensing Letters 3(2): 151–159. CrossRefGoogle Scholar
  3. Gonzalez RC, Woods RE, Eddins SL (2004) Digital Image Processing Using MATLAB. Third New Jersey: Prentice Hall: pp 237–241.Google Scholar
  4. Graham RL, Yao FF (1983) Finding the convex hull of a simple polygon. Journal of Algorithms 4(4): 324–331. CrossRefGoogle Scholar
  5. Guo QR, Xu JL, Sun SS, et al. (2010) Color image segmentation method based on color barycenters and K–means algorithm. Journal of Zhejiang Sci–Tech University 27(04): 580–584. (In Chinese) Google Scholar
  6. Hassouna H, Melgani F, Mokhtari Z (2015) Spatial contextual Gaussian process learning for remote–sensing image classification. Remote Sensing Letters 6(7): 519–528. CrossRefGoogle Scholar
  7. Mayer H, Wiedemann C, et al. (1997) Evaluation of automatic road extraction. International Archives of Photogrammetry and Remote Sensing 32 (3 SECT 4W2): 151–160.Google Scholar
  8. Hu Y, Zhang XC, Ma ZZ, et al. (2016) Rural residential area extraction from UAV remote sensing imagery. Remote Sensing for Land & Resources 28(03): 96–101. (In Chinese) Google Scholar
  9. Ibraheem NA, Hasan MM, Khan RZ, et al. (2012) Understanding color models: a review. ARPN Journal of Science and Technology 2(3): 265–275.Google Scholar
  10. Jin XY, Davis CH (2005) Automated building extraction from high–resolution satellite imagery in urban areas using structural, contextual, and spectral information. EURASIP Journal on Advances in Signal Processing 14: 2196–2206. Google Scholar
  11. Liu HF, Chang QR, Li FL (2013) Urban building extraction from high–resolution multi–spectral image with object–oriented classification. Journal of Northwest A&F University(Nat. Sci. Ed.) 41(10): 221–227, 234. (In Chinese)Google Scholar
  12. Li XH, Wu JF, Zhang GF, et al. (2013) New color image segmentation based on watershed and region merging. Journal of Electronic Measurement and Instrument 27(03): 247–252. (In Chinese) Google Scholar
  13. Lu H, Fu X, Liu C, Li LG, He YX, LI NW (2017) Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning. Journal of Mountain Science 14(04): 731–741. CrossRefGoogle Scholar
  14. Maesschalck RD, Jouan–Rimbaud D, Massart DL (2000) The mahalanobis distance. Chemometrics and intelligent laboratory systems 50(1): 1–18. CrossRefGoogle Scholar
  15. Maggiori E, Tarabalka Y, Charpiat G, et al. (2017) Convolutional neural networks for large–Scale remote sensing image classification. IEEE Transactions on Geoscience and Remote Sensing 55 (2): 645–657. CrossRefGoogle Scholar
  16. Mahalanobis PC (1936) On the generalized distance in statistics. Proceedings of the National Institute of Sciences (Calcutta) 2: 49–55.Google Scholar
  17. Muller S, Zaum DW (2005) Robust building detection in aerial images. International Archives of Photogrammetry and Remote Sensing 36(B2/W24): 143–148.Google Scholar
  18. Pang XM, Min ZJ, Kan JM (2011) Color image segmentation based on HSI and LAB color space. Journal of Guangxi University: Natural Science Edition 36(06): 976–980. (In Chinese) Google Scholar
  19. Rottensteiner F, Trinder J, Clode S, et al. (2004) Fusing airborne laser scanner data and aerial imagery for the automatic extraction of buildings in densely built–up areas. International Archives of Photogrammetry and Remote Sensing 35(B3): 512–517.Google Scholar
  20. Rusu RB, Marton ZC, Blodow N, et al. (2008) Towards 3D Point cloud based object maps for household environments. Robotics and Autonomous Systems 56(11): 927–941. CrossRefGoogle Scholar
  21. Saito S, Aoki Y (2015) Building and road detection from large aerial imagery. SPIE/IS&T Electronic Imaging: 94050K–94050K–12. Google Scholar
  22. Shi J, Chen CK (2011) Mahalanobis distance–based semisupervised discriminant analysis for face recognition. Journal of Beijing University of Aeronautics and Astronautics 37(12): 1589–1593. (In Chinese) Google Scholar
  23. Su TF, Zhang SW (2017) Local and global evaluation for remote sensing image segmentation. ISPRS Journal of Photogrammetry and Remote Sensing 130: 256–276. CrossRefGoogle Scholar
  24. Wang C, Chen M, Liu Y, et al. (2010) Extraction of color Doppler flow image of left heart by color image segmentation. Chinese Journal of Medical Imaging 18(3): 272–275. (In Chinese) Google Scholar
  25. Xiao PF, Zhang XL, Wang DG, et al. (2016) Change detection of built–up land: A framework of combining pixel–based detection and object–based recognition. ISPRS Journal of Photogrammetry and Remote Sensing 119: 402–414. CrossRefGoogle Scholar
  26. Xu SH, Liu JP, Hu MY (2010) Automatic building detection in color aerial images based on region segmentation. Journal of Liaoning Technical University (Natural Science) 29(06): 1058–1061. (In Chinese)Google Scholar
  27. Ye QX, Gao W, Wang WQ, et al. (2004) A color image segmentation algorithm by using color and spatial information. Journal of Software 15(04): 522–530. (In Chinese) Google Scholar

Copyright information

© Science Press, Institute of Mountain Hazards and Environment, CAS and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Faculty of Geosciences and Environmental EngineeringSouthwest Jiaotong UniversityChengduChina
  2. 2.Center of Land Acquisition and Consolidation in Sichuan ProvinceChengduChina

Personalised recommendations