Abstract Stand counts is one of the most common ways farmers assess plant growth conditions and management practices throughout the season. The conventional method for early-season stand count is through manual inspection, which is time-consuming, laborious, and spatially limited in scope. In recent years, Unmanned Aerial Vehicles (UAV) based remote sensing has been widely used in agriculture to provide low-altitude, high spatial resolution imagery to assist decision making. In this project, we designed a system that uses geometric descriptor information with deep neural networks to determine early-season maize stands from relatively low spatial resolution (10 to 25 mm) aerial data, which covers a relatively large area (10 to 25 hectares). Instead of detecting individual crops in a row, we process the entire row at one time, which significantly reduces the requirements for the clarity of the crops. Besides, our new MaxArea Mask Scoring RCNN algorithm could segment crop-rows out in each patch image, regardless of the terrain conditions. The robustness of our scheme was tested on data collected at two different fields in different years. The accuracy of the estimated emergence rate reached up to 95.8%. Due to the high processing speed of the system, it has the potential for real-time applications in the future.

中文翻译：

---

使用深度神经网络改进作物行检测，用于无人机图像中的早季玉米林分计数

摘要 林分计数是农民评估整个季节植物生长条件和管理实践的最常见方式之一。传统的早季林分计数方法是通过人工检查，费时费力，而且范围空间有限。近年来，基于无人机（UAV）的遥感已广泛应用于农业，以提供低空、高空间分辨率的图像以辅助决策。在这个项目中，我们设计了一个系统，该系统使用几何描述符信息和深度神经网络，从相对较低的空间分辨率（10 到 25 毫米）航拍数据中确定早季玉米林分，覆盖面积相对较大（10 到 25 公顷） . 我们不是检测一行中的单个作物，而是一次处理整行，这大大降低了对作物透明度的要求。此外，我们新的 MaxArea Mask Scoring RCNN 算法可以在每个补丁图像中分割出裁剪行，而不管地形条件如何。我们的方案的稳健性在不同年份在两个不同领域收集的数据进行了测试。估计出苗率的准确率高达95.8%。由于系统处理速度快，因此具有未来实时应用的潜力。