基于卫星图像的平原植保作业区域检测研究

Research on the detection of plain plant protection operation area based on satellite image

植保无人机在植保作业中发挥着重要的作用.植保无人机在作业前需要感知作业区域的地形等信息,为作业规划提供二维的数学计算环境.目前研究多建立在高分辨率的遥感影像基础之上,民用获取有难度.基于分辨有限的民用高德地图卫星图像,采用图像处理获取封闭作业区域,具体过程为使用改进的边缘检测算子获得作业区域轮廓,形态学运算与断点修补对轮廓断点进行修补,二值图像像素颜色比例统计得到作业区域面积.根据该方法与开发的面积测量工具进行验证,结果表明拟合度最高达到99.53%,均值也达到95.78%.通过分析,结果对比拟合度高,能较好地得到植保作业区域的轮廓,可以为作业规划提供较为精确的二维数学计算环境.

Plant protection UAV is playing an increasingly important role in plant protection operations. Plant protection UAVs need to perceive the terrain and other information of the operation area before operation to provide a two-dimensional mathematical calculation environment for operation planning. At present, most studies are based on high-resolution remote sensing images, which are difficult to obtain for civilian use. Based on the civil AMAP satellite image with limited resolution, the closed operating area was obtained by image processing. The specific process was to obtain the contour of the operating area by using the improved edge detection operator, repair the contour breakpoint by morphological operation and breakpoint repair, and obtain the area of the operating area by the color ratio statistics of binary image pixels. The method was validated with the developed area measuring tool, and the results showed that the highest fitting degree was 99.53% and the mean value was 95.78%. Through analysis, the results have a high degree of comparison, and can better obtain the outline of plant protection operation area, which can provide a more accurate two-dimensional mathematical calculation environment for operation planning.