面向对象的冬小麦种植面积遥感估算研究

Object oriented estimation of winter wheat planting area using remote sensing data

种植面积的遥感估算是冬小麦遥感估产的重要基础性工作之一。该文主要的研究内容是基于Landsat ETM+遥感影像,利用面向对象的分类方法提取山东省桓台县冬小麦种植面积。以山东省桓台县为例,选择Landsat ETM+L1G遥感影像,通过影像分割和基于知识的面向对象的分类方法准确地提取研究区冬小麦面积。以乡镇为单位将其结果同统计年鉴数据对比分析,误差最大的是果里镇,误差在95 hm2,整个研究区的提取误差是-111 hm2,能够满足实际应用的需求。

Estimating winter wheat planting area using remote sensing imagery is the basis for estimating winter wheat yield. This research deals with the estimation of planting area of winterwheat in Huantai County, Shandong Province, based.on Landsat ETM＋ imagery. Image segmentation was done after data preprocessing, then knowledge-based object oriented classification was conducted to extract wheat area information. Accuracy assessment proves that ideal classification results can be obtained, the area-estimating error of the whole study area is - 111 hm^2, and the largest area- estimating error in Guoli County is 95hm^2, which can meet the requirement of application.