Graduate School of Agriculture, Kyoto University, Kyoto, Japan.
Field Science Education and Research Centre, Kyoto University, Kyoto, Japan.
Sci Rep. 2021 Jan 13;11(1):903. doi: 10.1038/s41598-020-79653-9.
The identification and mapping of trees via remotely sensed data for application in forest management is an active area of research. Previously proposed methods using airborne and hyperspectral sensors can identify tree species with high accuracy but are costly and are thus unsuitable for small-scale forest managers. In this work, we constructed a machine vision system for tree identification and mapping using Red-Green-Blue (RGB) image taken by an unmanned aerial vehicle (UAV) and a convolutional neural network (CNN). In this system, we first calculated the slope from the three-dimensional model obtained by the UAV, and segmented the UAV RGB photograph of the forest into several tree crown objects automatically using colour and three-dimensional information and the slope model, and lastly applied object-based CNN classification for each crown image. This system succeeded in classifying seven tree classes, including several tree species with more than 90% accuracy. The guided gradient-weighted class activation mapping (Guided Grad-CAM) showed that the CNN classified trees according to their shapes and leaf contrasts, which enhances the potential of the system for classifying individual trees with similar colours in a cost-effective manner-a useful feature for forest management.
利用遥感数据进行树木识别和制图，以应用于森林管理，这是一个活跃的研究领域。之前使用机载和高光谱传感器提出的方法可以非常准确地识别树种，但成本高昂，因此不适合小规模的森林管理者。在这项工作中，我们使用无人驾驶飞行器 (UAV) 拍摄的红-绿-蓝 (RGB) 图像和卷积神经网络 (CNN) 构建了用于树木识别和制图的机器视觉系统。在该系统中，我们首先计算了由 UAV 获得的三维模型的斜率，并使用颜色、三维信息和斜率模型自动将森林的 UAV RGB 照片分割成几个树冠物体，最后对每个树冠图像应用基于对象的 CNN 分类。该系统成功地对包括几种树木物种在内的 7 个树木类进行了分类，分类准确率超过 90%。引导梯度加权类激活映射（Guided Grad-CAM）表明，CNN 根据树木的形状和叶子对比度进行分类，这增强了该系统以经济有效的方式对颜色相似的单个树木进行分类的潜力，这是森林管理的一个有用特征。
