基于无人机遥感的花生氮营养反演研究

氮素是影响花生生长发育的重要因素之一，目前传统凯氏定氮法测定步骤繁琐且需要时间较长，而无人 机遥感具有实时、灵活、低成本的特点，因此，为实现对花生氮含量的快速、无损、准确监测，本研究利用大疆精灵4 号无人机搭载的可见光相机，获取不同生育期的可见光影像，运用神经网络算法，建立叶片数字图像彩色信息和叶 片氮含量的关系模型。结果表明，利用数字图像指标作为网络输入向量时，所构建模型的平均绝对偏差为1.5左 右，且以r、g、b(r=R/(R+G+B), g=G/(R+G+B), b=B/(R+G+B))和a, b, c (a=R+G, b=R+B, c=G+B)两种组合参数拟合效果最 好，平均绝对偏差为0.2左右，和真实值相差较小。通过检验发现，两种方法都能准确地预测出花生叶片氮含量，所 构建模型能快速、无损地测定花生植株的肥料状况。

Peanut nitrogen nutrition inversion based on unmanned aerial vehicle remote sensing

Nitrogen is one of the important factors affecting the growth and development of peanuts. At present, the traditional method of determining the nitrogen content of crops, Kjeldahl nitrogen determination method, is com? plicated and takes a long time. While unmanned aerial sensing has the characteristics of real-time, flexibility and low-cost. Therefore, in order to achieve rapid, non-destructive and accurate monitoring of peanut nitrogen content, the visible light camera carried by phantom 4 unmanned aerial vehicle was used to obtain visible light images of dif? ferent growth stages, and the neural network algorithm was used to establish the relationship model between digital image color information of leaves and the nitrogen content of leaves. The result showed that when the digital image index was used as the input vector of the network, the average absolute deviation of the constructed model was about 1.5, and the combination of r, g, b(r=R/(R+G+B), g=G/(R+G+B), b=B/(R+G+B))and a, b, c (a=R+G, b=R+B, c=G+ B) had the best fitting effect, and the average absolute deviation was about 0.2, which contained less error. Through comparison, both methods could accurately predict the value of nitrogen content in peanut leaves.