期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
融合kd tree邻域查询的深度学习点云分类网络 被引量:13
1
作者 马杰 王旭娇 +2 位作者 马鹏飞 杨立闯 王楠楠 《深圳大学学报(理工版)》 EI CAS CSCD 北大核心 2020年第1期79-83,共5页
为解决PointNet++精度较低、耗时较长,且对输入点的噪声敏感的缺陷,引入一种高效的k维树(k-dimensional tree,kd tree)邻域查询方法,通过构建kd tree查找查询点周围指定半径内的近邻点,构造局部区域集,完成在PointNet++分组层上的局部... 为解决PointNet++精度较低、耗时较长,且对输入点的噪声敏感的缺陷,引入一种高效的k维树(k-dimensional tree,kd tree)邻域查询方法,通过构建kd tree查找查询点周围指定半径内的近邻点,构造局部区域集,完成在PointNet++分组层上的局部特征提取.针对原网络训练过程中存在的过拟合问题,引入随机失活(dropout)正则化,减少网络收敛训练的时间.在Ubuntu14.04系统下搭建TensorFlow的图形处理器深度学习环境,并在ModelNet40数据集上进行训练和测试.实验结果表明,分别为当查询半径为0.1、0.2和0.3时,该查询方法的分类准确率分别为91.1%、92.1%和94.3%,皆优于PointNet++方法,且网络训练用时更短.改进后的结构在斯坦福三维语义分析数据集(Stanford 3D semantic parsing dataset)上进行语义分割实验平均交并比(mean intersection over union,MIoU)达57.2%,且其对于遮挡物体的鲁棒性更高. 展开更多
关键词 计算机神经网络 深度神经网络 深度学习 点云分类 邻域查询 k维树 modelnet40
下载PDF
Point Cloud Classification Network Based on Graph Convolution and Fusion Attention Mechanism
2
作者 Tengteng Song Zhao Li +1 位作者 Zhenguo Liu Yizhi He 《Journal of Computer and Communications》 2022年第9期81-95,共15页
The classification of point cloud data is the key technology of point cloud data information acquisition and 3D reconstruction, which has a wide range of applications. However, the existing point cloud classification ... The classification of point cloud data is the key technology of point cloud data information acquisition and 3D reconstruction, which has a wide range of applications. However, the existing point cloud classification methods have some shortcomings when extracting point cloud features, such as insufficient extraction of local information and overlooking the information in other neighborhood features in the point cloud, and not focusing on the point cloud channel information and spatial information. To solve the above problems, a point cloud classification network based on graph convolution and fusion attention mechanism is proposed to achieve more accurate classification results. Firstly, the point cloud is regarded as a node on the graph, the k-nearest neighbor algorithm is used to compose the graph and the information between points is dynamically captured by stacking multiple graph convolution layers;then, with the assistance of 2D experience of attention mechanism, an attention mechanism which has the capability to integrate more attention to point cloud spatial and channel information is introduced to increase the feature information of point cloud, aggregate local useful features and suppress useless features. Through the classification experiments on ModelNet40 dataset, the experimental results show that compared with PointNet network without considering the local feature information of the point cloud, the average classification accuracy of the proposed model has a 4.4% improvement and the overall classification accuracy has a 4.4% improvement. Compared with other networks, the classification accuracy of the proposed model has also been improved. 展开更多
关键词 Graph Convolution Neural Network Attention Mechanism modelnet40 Point Cloud Classification
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部