基于改进PointNet++模型的苗圃树木点云分类与分割  

Point Clouds Classification and Segmentation for Nursery Trees Based onImproved PointNet++ Model

作　　者：徐婕 刘慧[1] 沈跃[1] 杨官学[1] 周昊 王思远 Xu Jie;Liu Hui;Shen Yue;Yang Guanxue;Zhou Hao;Wang Siyuan(School of Electrical and Information Engineering,Jiangsu University,Zhenjiang 212013,Jiangsu,China)

机构地区：[1]江苏大学电气信息工程学院,江苏镇江212013

出　　处：《中国激光》2024年第8期185-195,共11页Chinese Journal of Lasers

基　　金：国家自然科学基金(32171908)。

摘　　要：激光点云技术可用于苗圃树木生长状态监测与管理,为农业植保机器人提供有效的靶标信息。为了进一步提高树种分类和树冠、树干内部分割的精准性,提出一种基于改进PointNet++的激光点云苗圃树木分类与分割方法。首先,调整PointNet++深度网络邻居点云的相对特征值,同时融合三维点云的低维和高维特征,充分利用各层级点云的特征。然后,将坐标注意力模块与注意力池化融合,进一步增强局部特征提取的能力,提高分类和分割的准确性。最后,针对苗圃常见树木自制了包含7类苗圃景观树木点云的数据集并用于实验。实验结果表明,提出的树种识别方法总体精度可达92.50%,平均类别精度为94.22%;提出的树冠、树干分割方法的平均交并比为89.09%。所提方法在分类和分割性能方面均明显优于经典的PointNet和PointNet++,能够为苗圃树木检测识别和农业机器人作业提供更精确的信息。ion(SA)layers are used to extract the local features of the point clouds.Each SA layer consists of a sampling layer,a grouping layer,and a PointNet layer.The sampling layer employs the iterative farthest point sampling to select sampling points.Then,taking the sampling points as the center points,spherical regions with a fixed radius d are constructed as the local areas in the grouping layer.Each local area contains K neighboring points.As the number of layers increases,the radius d of the spherical region expands continuously.For larger local areas,the feature distribution adjustment module is employed to convert the relative features of neighboring points from linear to arc tangent,increasing the relative features of those closer to the central point while reducing the influence of distant neighboring points in each local area.Multilayer perceptrons(MLPs)are employed for extracting local features in the PointNet layer.To enhance the model’s capacity to capture important information,we integrate the coordinate attention(CA)module with attention pooling for extracting local features.Furthermore,in the final SA layer,the model concatenates the low-dimensional and high-dimensional features of sampled points,and employs fully connected networks to predict the category of the input point clouds.The segmentation branch utilizes the U-Net structure,and employs an interpolation method based on inverse distance weighted average with K nearest neighbors,combining with skip links across levels for feature propagation.Finally,the category of each point is obtained to realize segmentation.Results and Discussions For classification and segmentation experiments,we collect seven kinds of point clouds of common landscape trees in the nursery using the Livox Horizon laser.During the data collection process,the parameters of the laser are shown in Table 1,and more detailed information of the collected point clouds is shown in Table 2.To perform segmentation tasks,each group of collected point clouds is further processed by divid

关 键 词：遥感 激光雷达 深度学习 树种分类 苗圃树木树冠和树干分割 PointNet++ 

分 类 号：TN249[电子电信—物理电子学]