English

应用科学学报 ›› 2011, Vol. 29 ›› Issue (4): 390-396.doi: 10.3969/j.issn.0255-8297.2011.04.010

• 信号与信息处理 • 上一篇    下一篇

应用商空间理论的遥感影像多粒度合成分割

李刚1， 万幼川1， 管玉娟2   

  1. 1．武汉大学遥感信息工程学院，武汉430079
    2．上海大学期刊社，上海200444
  • 收稿日期:2011-03-09 修回日期:2011-04-27 出版日期:2011-07-30 发布日期:2011-07-30
  • 作者简介:李刚，博士生，研究方向：遥感图像处理、模式识别，E-mail: whulg@163.com；万幼川，博士，教授，博导，研究方向：遥感与 信息系统、数字城市、数字流域，E-mail: wych@public.wh.hb.cn
  • 基金资助:

    国家科技支撑计划项目基金(No.2011BAH12B03)；上海高校选拔培养优秀青年教师科研专项基金资助

Multi-granularity Synthesis Segmentation of Remote Sensing Image Based on Quotient Space Theory

LI Gang1, WAN You-chuan1, GUAN Yu-juan2   

  1. 1．School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
    2．Periodicals Agency, Shanghai University, Shanghai 200444, China
  • Received:2011-03-09 Revised:2011-04-27 Online:2011-07-30 Published:2011-07-30

PDF

1671

被引次数

10

摘要：

传统影像分割方法只能对影像进行单一粒度空间的分割，分割结果的准确性限于单一粒度空间，该文运用商空间理论提出一种遥感影像多粒度合成分割方法. 首先探讨多粒度影像分割的商空间模型，用影像数据场表达像元空间关系，用分形维数特征增强人工地物和自然场景的区分能力. 对灰度特征、影像数据场、分形维数分别进行分水岭分割和迭代自组织数据分析(ISODATA)聚类，获得多粒度分割结果. 最后基于粒度合成原理给出一个具体的多粒度影像分割的商空间合成算法. 实验表明该方法能充分利用各个粒度空间分割结果的优点，纠正了单一粒度空间的分割错误，分割结果更准确.

关键词: 分水岭变换, 多粒度合成分割, 商空间, 数据场, 分形维数

Abstract:

Abstract: Traditional segmentation method can only partition an image in a single granularity space, with segmentation accuracy limited to the single granularity space. This paper proposes a multi-granularity synthesis segmentation method for remote sensing images based on the quotient space granular theory. A quotient space model of multi-granularity image segmentation is discussed. Image data field is used to express the spatial
correlation of pixels, and fractal dimension used to enhance the capability of discrimination between artificial surface features and the natural scenes. The watershed algorithm and iterative self-organizing data analysis technique (ISODATA) are applied to the gray image, data field image and fractal dimension image to produce multi-granularity segmentation results. This paper proposes a specific quotient space synthesis algorithm for
multi-granularity image segmentation. Experiments show that the proposed method can take full advantage of the segmentation result in every granular space. The multi-granularity synthesis segmentation is effective and can produce more accurate segmentation than that of a single granularity space.

Key words: quotient space, data field, fractal dimension, watershed transformation, multi-granularity synthesis segmentation

中图分类号: