| 超体素约束下的主动再学习LiDAR点云分类框架 |
| |
| 引用本文： | 谭玉慧,刘欣怡,张永军.超体素约束下的主动再学习LiDAR点云分类框架[J].测绘通报,2022,0(5):79-83+100. |
| |
| 作者姓名： | 谭玉慧 刘欣怡 张永军 |
| |
| 作者单位： | 武汉大学遥感信息工程学院, 湖北 武汉 430079 |
| |
| 基金项目： | 国家自然科学基金(41871368)； |
| |
| 摘 要： | 针对点云分类的监督方法需要大量的训练样本、人工标注成本高的问题,本文提出了一种超体素约束下的主动再学习点云分类方法。首先,对点云进行特征提取;然后,通过超体素约束下的主动学习方法选择训练样本并进行人工标注;最后,利用再学习方法进行后处理,通过迭代计算类别统计特征不断优化分类结果。试验结果表明,相比于使用全部训练样本,超体素约束的主动学习方法可以在不足全部样本6%的情况下,达相同的分类精度,从而大幅度减少了人工标注成本,且经过再学习算法后进一步提高了分类精度。
|
| 关 键 词： | 点云分类 超体素 主动学习 再学习 |
| 收稿时间： | 2021-06-21 |
A supervoxel-based active relearning framework for LiDAR point clouds classification |
| |
| TAN Yuhui,LIU Xinyi,ZHANG Yongjun.A supervoxel-based active relearning framework for LiDAR point clouds classification[J].Bulletin of Surveying and Mapping,2022,0(5):79-83+100. |
| |
| Authors: | TAN Yuhui LIU Xinyi ZHANG Yongjun |
| |
| Institution: | School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China |
| |
| Abstract: | To overcome the problem that the existing supervision methods require a large number of training samples and the high cost of manual labeling, a supervoxel-based active relearning method is proposed. Firstly, feature extraction is performed on the point cloud. Secondly, training samples are selected through the active learning method with supervoxel constraint and manually labeled. Finally, the relearning method is used for post-processing, and the classification results are continuously optimized by iterative calculation of category statistical features. The experimental results indicate that compared to using all training samples, the proposed method can achieve the same overall accuracy using less than 6% of all samples, which greatly reduces the cost of manual labeling. And the relearning algorithm also improves the classification accuracy. |
| |
| Keywords: | point cloud classification supervoxel active learning relearning |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《测绘通报》浏览原始摘要信息 |
| 点击此处可从《测绘通报》下载免费的PDF全文 |
|
