基于多判别参数混合方法的散乱点云特征提取
针对以往散乱点云特征提取算法存在尖锐特征点提取不完整以及无法保留模型边界点的问题，提出了一种多个判别参数混合方法的特征提取算法。对点云构建k-dtree，利用k-dtree建立点云K邻域；针对每个K邻域计算数据点曲率、点法向与邻域点法向夹角的平均值、点到邻域重心的距离、点到邻域点的平均距离，据此四个参数定义特征阈值和特征判别参数，特征判别参数大于阈值的点即为特征点。实验结果表明，与已有算法相比，该算法不仅可以有效提取尖锐特征点，而且能够识别边界点。...
Saved in:
| Published in | 计算机应用研究 Vol. 34; no. 9; pp. 2867 - 2870 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
西南科技大学制造过程测试技术省部共建教育部重点实验室,四川绵阳621010
2017
西南科技大学制造科学与工程学院,四川绵阳,621010%西南科技大学制造科学与工程学院,四川绵阳621010 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1001-3695 |
| DOI | 10.3969/j.issn.1001-3695.2017.09.067 |
Cover
| Summary: | 针对以往散乱点云特征提取算法存在尖锐特征点提取不完整以及无法保留模型边界点的问题，提出了一种多个判别参数混合方法的特征提取算法。对点云构建k-dtree，利用k-dtree建立点云K邻域；针对每个K邻域计算数据点曲率、点法向与邻域点法向夹角的平均值、点到邻域重心的距离、点到邻域点的平均距离，据此四个参数定义特征阈值和特征判别参数，特征判别参数大于阈值的点即为特征点。实验结果表明，与已有算法相比，该算法不仅可以有效提取尖锐特征点，而且能够识别边界点。 |
|---|---|
| Bibliography: | 51-1196/TP point cloud; feature extraction; K-nearest neighbors; boundary points Chen Longa, Cai Yonga,b, Zhang Jianshenga, Xiang Beipinga,b （a. School of Manufacturing Science ＆ Engineering, b. Key Laboratory of Testing Technology for Manufacturing Process, Southwest University of Science ＆ Technology, Mianyang Sichuan 621010, China） This paper proposed an algorithm of extracting feature points based on multiple parameters hybridization method, which aimed to solve the problem that previous algorithms existed, including sharp feature points extraction were incomplete, and could not retain boundary points. Firstly, this algorithm constructed a k-d tree to establish K-nearest neighborhood of the point cloud. Then, it calculated the data point curvature, average vector angle between the point and its K-nearest neighbor- hood points, distance from point to its neighborhood gravity center, average distance from point to its neighborhood points for each K-nearest neighborhood. Finally, according to the four parameter |
| ISSN: | 1001-3695 |
| DOI: | 10.3969/j.issn.1001-3695.2017.09.067 |