测绘通报 ›› 2022, Vol. 0 ›› Issue (5): 26-31.doi: 10.13474/j.cnki.11-2246.2022.0136

• 水体变化遥感监测 • 上一篇    下一篇

顾及GF-3影像纹理特征的洪涝范围提取方法

郁宗桥, 王育红, 刘文宋, 左雨芳, 冯锋   

  1. 江苏师范大学地理测绘与城乡规划学院, 江苏 徐州 221116
  • 收稿日期:2021-04-20 发布日期:2022-06-08
  • 通讯作者: 刘文宋。E-mail:liuwensongupc@163.com
  • 作者简介:郁宗桥(1994-),男,硕士生,研究方向为SAR影像目标识别。E-mail:1030085785@qq.com
  • 基金资助:
    江苏省自然科学青年基金(BK20201026);江苏师范大学科研基金(19XSRX006);江苏师范大学研究生科研与实践创新计划(2020XKT056)

Flood extent extraction method based on the texture features of GF-3 images

YU Zongqiao, WANG Yuhong, LIU Wensong, ZUO Yufang, FENG Feng   

  1. School of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou 221116, China
  • Received:2021-04-20 Published:2022-06-08

摘要: 洪涝灾害给社会、经济造成巨大损失,及时、快速监测洪涝范围在抗灾救灾中具有重要意义。合成孔径雷达(SAR)由于其主动式微波成像的机理,可为全天时、全天候、大范围洪涝灾害监测提供支持。本文首先以高分三号(GF-3)卫星影像为数据源,基于灰度共生矩阵(GLCM)、局部二值模式(LBP)等6种纹理描述方法提取138个SAR影像纹理特征;然后利用随机森林(RF)指标重要性评估功能,筛选出重要性得分较高的纹理特征进行水体信息提取;最后结合数学形态学对初始水体提取结果进行后处理,评估安徽巢湖附近区域洪涝灾害。试验表明,本文方法的水体提取精度优于传统阈值法(Otsu)及分类算法(KNN和SVM),可有效提取洪涝灾害的影响范围,为选取合适的SAR影像纹理特征进行洪涝范围快速监测提供参考。

关键词: 洪涝灾害, 纹理特征, 随机森林, GF-3, 巢湖

Abstract: Flood disaster will cause huge losses to local society and economy, timely and rapid monitoring of flood range is of great significance in disaster relief. Synthetic aperture radar (SAR) can provide support for all-day, all-weather and large-scale flood monitoring due to its active microwave imaging mechanism. This paper takes GF-3 satellite images as data source, and extracts 138 image texture features of GF-3 based on six texture description methods, such as the gray level co-occurrence matrix (GLCM) and the local binary pattern (LBP), etc. Then, the texture features with high importance scores are selected for water information extraction by using the index importance evaluation function of the random forest (RF) algorithm. Finally, the initial water extraction results are post-processed combined with mathematical morphology to evaluate the flood disaster near Chaohu Lake in Anhui province. The experiments show that the water extraction accuracy of the proposed method is better than the results of traditional threshold method (Otsu) and classification (KNN and SVM) algorithms. And the proposed method can effectively extract the influence range of flood disaster, and provide a reference for selecting appropriate texture features of SAR images for rapid monitoring of flood range.

Key words: flood disaster, texture feature, random forest, GF-3, Chaohu lake

中图分类号: