Volume XLI-B7
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B7, 351-358, 2016
https://doi.org/10.5194/isprs-archives-XLI-B7-351-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B7, 351-358, 2016
https://doi.org/10.5194/isprs-archives-XLI-B7-351-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

  21 Jun 2016

21 Jun 2016

COMBINING SPECTRAL AND TEXTURE FEATURES USING RANDOM FOREST ALGORITHM: EXTRACTING IMPERVIOUS SURFACE AREA IN WUHAN

Zhenfeng Shao1,2, Yuan Zhang1, Lei Zhang1, Yang Song3, and Minjun Peng4 Zhenfeng Shao et al.
  • 1State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan, China 430079
  • 2Shenzhen Research and Development Center of State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Shenzhen, China, 518057
  • 3Guangzhou urban planning design &survey research institute, 10 Jianshedamalu, Guangzhou, China, 510060
  • 4Wuhan city land resources and Planning Information Center, 13 Sanyang Road, Wuhan, China, 430014

Keywords: Impervious surface area, Random forest, Texture features

Abstract. Impervious surface area (ISA) is one of the most important indicators of urban environments. At present, based on multi-resolution remote sensing images, numerous approaches have been proposed to extract impervious surface, using statistical estimation, sub-pixel classification and spectral mixture analysis method of sub-pixel analysis. Through these methods, impervious surfaces can be effectively applied to regional-scale planning and management. However, for the large scale region, high resolution remote sensing images can provide more details, and therefore they will be more conducive to analysis environmental monitoring and urban management. Since the purpose of this study is to map impervious surfaces more effectively, three classification algorithms (random forests, decision trees, and artificial neural networks) were tested for their ability to map impervious surface. Random forests outperformed the decision trees, and artificial neural networks in precision. Combining the spectral indices and texture, random forests is applied to impervious surface extraction with a producer’s accuracy of 0.98, a user’s accuracy of 0.97, and an overall accuracy of 0.98 and a kappa coefficient of 0.97.