Acta Geodaetica et Cartographica Sinica ›› 2017, Vol. 46 ›› Issue (11): 1880-1890.doi: 10.11947/j.AGCS.2017.20170074

Previous Articles     Next Articles

Change Detection Method for High Resolution Remote Sensing Images Using Random Forest

FENG Wenqing1, SUI Haigang1, TU Jihui1,2, SUN Kaimin1, HUANG Weiming3   

  1. 1. State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
    2. Electronics & Information School of Yangtze University, Jingzhou 434023, China;
    3. Department of Physical Geography and Ecosystem Science, Lund University, Lund 22362, Sweden
  • Received:2017-03-01 Revised:2017-09-09 Online:2017-11-20 Published:2017-12-05
  • Supported by:

    The National Key Research and Development Program of China (No. 2016YFB0502603) Open Research Fund of State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (No. 16E01) The National Natural Foundation of China (NSFC)(No. 41471354)

Abstract:

Studies based on object-based image analysis (OBIA) representing the paradigm shift in remote sensing image change detection (CD) have achieved remarkable progress in the last decade.Their aim has been developing more intelligent interpretation analysis methods in the future.The prediction effect and performance stability of random forest (RF),as a new kind of machine learning algorithm,are better than many single predictors and integrated forecasting method. This paper presents a novel RF OBIA method for high resolution remote sensing image CD that makes full use of the advantages of RF and OBIA. Firstly,the entropy rate segmentation algorithm is used to segment the image for the purpose of measuring the homogeneity of super-pixels. Then the optimal image segmentation result is obtained from the evaluation index of the optimal super-pixel number.Afterwards,the spectral features and Gabor features of each super-pixelareextracted and used as feature datasets for the training of RF model.On the basis of the initial pixel-level CD result,the changed and unchanged samples are automatically selected and used to build the classifier model in order to get the final object-level CD result.Experimental results on Quickbird,IKONOS and SPOT-5 multi-spectral images show that the proposed method out performs the compared methods in the accuracy of CD.

Key words: segmentation, super-pixel, feature, random forest, change detection

CLC Number: