多特征融合与残差优化的点云语义分割方法  

Point cloud semantic segmentation method based on multi-feature fusion and residual optimization

作　　者：杜静 蔡国榕[1] Du Jing;Cai Guorong(School of Computer Engineering,Jimei University,Xiamen 361000,China)

机构地区：[1]集美大学计算机工程学院,厦门361000

出　　处：《中国图象图形学报》2021年第5期1105-1116,共12页Journal of Image and Graphics

基　　金：国家自然科学基金项目(41971424,61701191);福建省教育厅科技项目(JAT190321,JAT190318,JAT190315);厦门市科技计划重大项目(3502Z20191018,3502Z20201007,3502Z20191022,3502Z20203057);厦门市海洋与渔业局科技项目(18CZB033HJ11);福建省自然科学基金项目。

摘　　要：目的当前的大场景3维点云语义分割方法一般是将大规模点云切成点云块再进行处理。然而在实际计算过程中,切割边界的几何特征容易被破坏,使得分割结果呈现明显的边界现象。因此,迫切需要以原始点云作为输入的高效深度学习网络模型,用于点云的语义分割。方法为了解决该问题,提出基于多特征融合与残差优化的点云语义分割方法。网络通过一个多特征提取模块来提取每个点的几何结构特征以及语义特征,通过对特征的加权获取特征集合。在此基础上,引入注意力机制优化特征集合,构建特征聚合模块,聚合点云中最具辨别力的特征。最后在特征聚合模块中添加残差块,优化网络训练。最终网络的输出是每个点在数据集中各个类别的置信度。结果本文提出的残差网络模型在S3DIS(Stanford Large-scale 3D Indoor Spaces Dataset)与户外场景点云分割数据集Semantic3D等2个数据集上与当前的主流算法进行了分割精度的对比。在S3DIS数据集中,本文算法在全局准确率以及平均准确率上均取得了较高精度,分别为87.2%,81.7%。在Semantic3D数据集上,本文算法在全局准确率和平均交并比上均取得了较高精度,分别为93.5%,74.0%,比GACNet(graph attention convolution network)分别高1.6%,3.2%。结论实验结果验证了本文提出的残差优化网络在大规模点云语义分割的应用中,可以缓解深层次特征提取过程中梯度消失和网络过拟合现象并保持良好的分割性能。Objective The semantic segmentation of 3D point cloud is to take the point cloud as input and output the semantic label of each point according to the category.However,the existing semantic segmentation methods based on 3D point cloud are mainly limited to processing on small-scale point cloud blocks.When a large-scale point cloud is cut into small point clouds,the geometric features of the cut boundary can be easily destroyed,which results in obvious boundary phenomena.In addition,traditional semantic segmentation deep networks have difficult in meeting the computational efficiency requirements of large-scale data.Therefore,an efficient deep learning network model that directly takes the original point cloud as input for point cloud semantic segmentation is urgently needed.However,most networks still choose to input small point cloud blocks for training,mainly because there are many difficulties in directly handling point clouds in large scenes.The first is that the spatial size and number of points of the 3D point cloud data collected through sensor scanning are uncertain.This requires that the network does not have a specific number of input points and is not sensitive to the number of points.Second,the geometric structure of large scenes is more complicated than that of small-scale point cloud blocks,which increases the difficulty of segmentation.The third is that the direct processing of point clouds in large scenes will bring a lot of calculations,which poses a huge challenge to existing graphics processing unit(GPU)memory.The main obstacle to be overcome by our framework is to directly deal with large-scale 3D point clouds.For different point cloud spatial structures and points,they can be directly input into the network for training under the condition of ensuring time complexity and space complexity.MethodIn this study,a residual optimization network based on large-scale point cloud semantic segmentation is proposed.First,we choose random sampling as the down-sampling strategy,and its calculation time is

关 键 词：计算机视觉 3维点云 大场景 语义分割 多特征融合 残差网络 

分 类 号：S771[农业科学—森林工程]