测绘学报 ›› 2014, Vol. 43 ›› Issue (5): 493-499.

• 学术论文 • 上一篇    下一篇

高分辨率遥感影像的压缩纹理元分类

金晶1,邹峥嵘陶超1   

  • 收稿日期:2013-01-17 修回日期:2014-02-23 出版日期:2014-05-20 发布日期:2014-06-05
  • 通讯作者: 金晶 E-mail:csujinjing@sina.com
  • 基金资助:

    高分辨率遥感数据精处理和空间信息智能转化的理论与方法

Compressed Texton Based High Resolution Remote Sensing Image Classification

  • Received:2013-01-17 Revised:2014-02-23 Online:2014-05-20 Published:2014-06-05

摘要:

针对传统的高分辨率遥感影像分类中特征提取复杂,特征维数大等问题,提出一种新颖,简单,高效的纹理特征提取方法。首先,利用随机投影对基于原始像素灰度值的纹理元矢量进行降维,将其投影到压缩的纹理特征子空间。然后,在压缩子空间中对各类纹理元进行聚类,将聚类中心作为纹理字典,得到局部纹理特征集。最后,将样本中包含的纹理元编码到纹理字典中对应距离最近的词汇,得到样本的视觉词汇图,并融合词汇统计直方图与词汇二阶矩信息作为最终的纹理表达。通过两组实验,验证了本文方法能够有效的表达纹理,提高分类精度。

关键词: 高分辨率遥感, 随机投影, 纹理特征, 纹理元, 视觉词汇, 分类

Abstract:

In order to avoid the high computational-complexity inherited in traditional texture extraction method, a novel, simple, yet effective textural feature extraction method for high resolution remote sensing image classification is proposed in this paper. First, the original texture extracted from local image patches are projected into the compressed sub-space using the random projection technique. Then, the texture dictionary which represents local features is learned with k-means in the compressed domain for each class. Finally, the visual word map is formed by coding every texton in the samples to the nearest word in the texture dictionary, and then the histogram of the visual words map and the second moment of the words are fused as the final textural feature. The propose method is proved to be effective for texture representation and improving accuracy for high remote sensing image classification by two groups of experiments.

Key words: High resolution remote sensing, Random projection, Texture feature, Texton, Visual words, Classification

中图分类号: