Hierarchical Decision Tree for Change Detection Using High Resolution Remote Sensing Images

  • Zhiwei XieEmail author
  • Min Wang
  • Yaohui Han
  • Dayong Yang
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 980)


In order to improve the classification accuracy of high resolution change detection, the key technologies such as segmentation scale determination, features selection and classifier use are studied, and a change detection method using hierarchical decision tree is proposed. Firstly, fractal net evolution approach was used to obtain image objects, and the optimal scales of vegetation, water, and man-made objects were determined by evaluation index based on classification accuracy. Second, the feature spaces of man-made, water and vegetation objects are constructed. Then, the hierarchical decision tree classification method with the optimal segmentation scales is applied to multi-temporal high resolution remote sensing images. Finally, change detection was implemented by comparing the multi-temporal classification results. The multi-temporal high resolution remote sensing images in Wuhan Lujiazhuang were chosen as the experimental data. The experiments show that the method is effective.


Image objects Optimal segmentation scale Ratio index Hierarchical decision tree Change detection 


  1. 1.
    Aplin, P., Atkinson, P.M., et al.: Per-field classification of land use using the forthcoming very fine spatial resolution satellite sensors: problems and potential solutions. In: Advances in Remote Sensing and GIS Analysis, pp. 219–239. Wiley, Chichester (1999)Google Scholar
  2. 2.
    Willhauck, G., Schneider, T., et al.: Comparison of object oriented classification techniques and standard image analysis for the use of change detection between SPOT multispectral satellite images and aerial photos, pp. 45–50. ISPRS, Amsterdam (2005)Google Scholar
  3. 3.
    Fan, H.: Case study on image differencing method for land use change detection using thematic data in Renhe District of Panzhihua. J. Remote. Sens. 01, 75–80 (2001)Google Scholar
  4. 4.
    Frate, F.D., Schiavon, G., Solimini, C.: Application of neural networks algorithms to Quick Bird imagery for classification and change detection of urban areas. In: Geoscience and Remote Sensing Symposium, pp. 1091–1094 (2004)Google Scholar
  5. 5.
    Repaka, S.R.: Comparing spectral-object-based approaches for extracting and classifying transportation features using high-resolution multi-spectral satellite imagery. Mississippi State University (2005)Google Scholar
  6. 6.
    Zhu, J.: The key technology of change detection using high resolution remotely sensed imagery. Zhejiang University, Hangzhou (2011)Google Scholar
  7. 7.
    Lao, X.: The research of object-based high resolution remote sensing land use change detection. Zhejiang University, Hangzhou (2013)Google Scholar
  8. 8.
    Xu, G.: Research on object-oriented change detection technology of remote sensing images. Information Engineering University, Zhengzhou (2011)Google Scholar
  9. 9.
    Wang, L.: Analyzing classification and segmentation parameters selection in high resolution remote sensing image based on object. Central South University, ChangshaGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Transportation EngineeringShenyang Jianzhu UniversityShenyangChina
  2. 2.Faculty of Geosciences and Environmental EngineeringSouthwest Jiaotong UniversityChengduChina

Personalised recommendations