摘要
针对传统遥感技术提取芦笋种植面积精度不高的问题,根据芦笋的种植特点,该文以山东省曹县为研究区域,以Landsat 8影像为研究数据,提出了芦笋种植面积的提取方法。通过分析芦笋种植区与其他地物归一化差值植被指数特征,首先利用阈值分割方法去除水体、小麦地物,进一步分析芦笋种植区、建筑物和道路等的影像二维特征空间,发现芦笋种植区的土壤线分布规律,并通过波段运算结果确定芦笋种植区阈值,最后进行芦笋种植面积提取。结果表明,曹县的芦笋种植面积为14626.55ha^2,总体精度为84.85%。
The traditional method of extracted cash crop planting area by remote sensing has been widely carried out. However,it is not suitable for the planting area extraction of asparagus. Aiming the deficiency of the existing methods, this paper considered the characteristics of asparagus production. Taking Caoxia county as the study area, the paper studied the method of extraction of asparagus planting area by using Landsat 8 images. By comparing the different NDVI between the asparagus planting area and other objects,this paper first removed the water and wheat field by NDV1 threshold segmentation method, and found the distribution of soil line by further analyzing the two-dimensional feature space of the asparagus planting area, buildings and roads. Finally, the asparagus planting area was extracted through the defined thresholds. The results showed that the asparagus planting area is 14626.55ha2 acres in Caoxian county, where the accuracy achieves 84.85%.
出处
《遥感信息》
CSCD
北大核心
2016年第1期106-109,共4页
Remote Sensing Information
基金
山东省农业重大应用技术创新课题(2012CX90204)
关键词
特征空间
芦笋
种植面积提取
土壤线
遥感影像
feature space
asparagus
planting area extraction
soil line remote sensing image