摘要
针对安徽省蚌埠市农作物水旱交错的特点,提出利用多时相中分辨率遥感影像,基于农作物的物候期特征选择合适的影像数据,采用面向对象的分析方法,构建水旱交错区农作物信息提取模式,进行农作物信息提取。蚌埠市农作物信息提取实验表明,该方法简单易行,有效避免了"椒盐现像",总体分类精度达91.7%,对于准确了解水旱交错地区农作物的面积及其分布情况,具有重要的应用价值。
According to the staggered distribution characteristics of crops in Bengbu City, an extraction mode was established by using multi-temporal medium-resolution images. By analy- zing the spectral characteristics and time series NDVI of main crops, the proper extraction fea- tures and the optimum temporal images were selected. Then, an extraction mode based on ob- ject-based information analysis method was established. The experimental results show that the extraction total accuracy of crops information reached up to 91.7~. Using this method one can avoid "salt and pepper phenomenon" and monitor the distribution of crops in transitional zone of Qinling-Huahe correctly and efficiently.
出处
《金陵科技学院学报》
2017年第1期72-76,共5页
Journal of Jinling Institute of Technology
基金
金陵科技学院博士启动基金(jit-b-201605)
金陵科技学院校级激励项目(jit-2016-jlxm-06)
关键词
蚌埠市
水旱交错
物候特征
多时相影像
面向对象的分析方法
Bengbu City
staggered zone of crops
phenological characteristics
multi-temporal images
object-based analysis