ABSTRACT

It is a crucial step locating the maize plant or even its target location precisely during the intelligent agricultural equipment working in farmland. Therefore, the segmentation of plants from the background image is one of the important research contents of agricultural machine vision. Under the background of significant color difference, the current method can effectively complete maize canopy segmentation and plant location identification. However, under the background of no-significant color difference, there is no robust and high-precision method for maize canopy segmentation and plant location identification. In this study, it was found that the grayscale of maize canopy had gradient distribution trend along the radial direction. The Hue Saturation Value color space and Support Vector Machine method was used to segment 600 maize canopy images, then the polynomial regression method was used to find out the functional relationship between grayscale gradient and canopy diameter. The functional relationship gave identification results of canopy central region under different gray gradient distribution. The result provided a theoretical basis for accurate identification and rapid location of maize plant center at seedling stage, and provided accurate position coordinate and yaw information for field navigation of agricultural intelligent equipment such as plant protection UAV.

摘要

这是至关重要的一步，要在农田中使用智能农业设备的过程中准确地定位玉米植物甚至目标位置。因此，从背景图像中进行植物分割是农业机器视觉的重要研究内容之一。在明显色差的背景下，当前方法可以有效地完成玉米冠层分割和植物位置识别。然而，在无明显色差的背景下，没有鲁棒且高精度的玉米冠层分割和植物位置识别方法。在这项研究中，发现玉米冠层的灰度在径向上具有梯度分布趋势。利用Hue Saturation Value色彩空间和支持向量机方法对600个玉米冠层图像进行分割，然后采用多项式回归方法找出灰度梯度与冠层直径之间的函数关系。该函数关系给出了不同灰度梯度分布下冠层中心区域的识别结果。研究结果为准确识别和快速定位玉米植株中心在苗期提供了理论依据，为植保无人机等农业智能设备的野外导航提供了准确的位置坐标和偏航信息。函数关系给出了不同灰度梯度分布下冠层中心区域的识别结果。研究结果为准确识别和快速定位玉米苗期的植物中心提供了理论依据，为植保无人机等农业智能设备的野外导航提供了准确的位置坐标和偏航信息。该函数关系给出了不同灰度梯度分布下冠层中心区域的识别结果。研究结果为准确识别和快速定位玉米植株中心在苗期提供了理论依据，为植保无人机等农业智能设备的野外导航提供了准确的位置坐标和偏航信息。