| 基于2D-3D语义传递的室内三维点云模型语义分割 |
| |
| 引用本文： | 熊汉江,郑先伟,丁友丽,张艺,吴秀杰,周妍.基于2D-3D语义传递的室内三维点云模型语义分割[J].武汉大学学报(信息科学版),2018,43(12):2303-2309. |
| |
| 作者姓名： | 熊汉江 郑先伟 丁友丽 张艺 吴秀杰 周妍 |
| |
| 作者单位： | 1.武汉大学测绘遥感信息工程国家重点实验室, 湖北 武汉, 430079 |
| |
| 基金项目： | 国家重点研发计划2018YFB0505401国家自然科学基金41871361国家自然科学基金41701445 |
| |
| 摘 要： | 针对现有三维点云模型重建对象化和结构化信息缺失的问题，提出一种基于图模型的二维图像语义到三维点云语义传递的算法。该算法利用扩展全卷积神经网络提取2D图像的室内空间布局和对象语义，基于以2D图像超像素和3D点云为结点构建融合图像间一致性和图像内一致性的图模型，实现2D语义到3D语义的传递。基于点云分类实验的结果表明，该方法能够得到精度较高的室内三维点云语义分类结果，点云分类的精度可达到73.875 2%，且分类效果较好。
|
| 关 键 词： | 语义三维点云模型 语义传递 语义标记 点云分类 |
| 收稿时间： | 2018-05-17 |
Semantic Segmentation of Indoor 3D Point Cloud Model Based on 2D-3D Semantic Transfer |
| |
| Affiliation: | 1.State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China2.School of Mathematics and Statistics, Wuhan University, Wuhan 430079, China |
| |
| Abstract: | In this paper, we propose an effective algorithm based on graph model for semantic transfer from 2D images to 3D point clouds, which can effectively solve the problem of objectification and lack of structured information of 3D point cloud model. Our proposed method uses the extended full convolutional neural network to extract the indoor space layout and object semantics of 2D images, and then implements the transfer of 2D semantics to 3D semantics based on the 2D image superpixels and 3D point clouds as nodes to construct a graph model of consistency between images and intra-image consistency. The experiment from 3D point cloud shows that the proposed method can obtain accurate indoor 3D point cloud semantic classification results. The accuracy of point cloud classification can reach 73.875 2%, and the classification effect is better. |
| |
| Keywords: | |
|
| 点击此处可从《武汉大学学报(信息科学版)》浏览原始摘要信息 |
|
点击此处可从《武汉大学学报(信息科学版)》下载全文 |
|
