A new process for the segmentation of high resolution remote sensing imagery

Zitong Chen, Zhongming Zhao, Peng Gong, Bing ZengInternational Journal of Remote Sensing 2006 · DOI

Abstract

Abstract The "watershed transformation" is a well‐known powerful tool for automated image segmentation. However, it is often computationally expensive and can produce over‐segmentation in situations of high gradient noise, quantity error and detailed texture. Here, a new method has been designed to overcome these inherent drawbacks. After pre‐processing the imagery using a nonlinear filter in order to filter the noise, an optimized watershed transformation is applied to provide an initial segmentation result. Then, a multi‐scale, multi‐characteristic merging algorithm is used to refine the segmentation. Preliminary results show promise in term of both segmentation quality and computational efficiency. Acknowledgments This study was supported in part by the High Tech Research and Development (863) Program under grant no. 2003AA13501 and the 100 Talents Program of the Chinese Academy of Sciences under grant no. kzcx0504.
BibTeX
@article{chen2006new,
  author = {Zitong Chen and Zhongming Zhao and Peng Gong and Bing Zeng},
  title = {{A new process for the segmentation of high resolution remote sensing imagery}},
  journal = {International Journal of Remote Sensing},
  year = {2006},
  doi = {10.1080/01431160600658131},
}

Loading related content...

Figure