• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Geoscience and Remote Sensing Letters >Multi-Scale Local Context Embedding for LiDAR Point Cloud Classification
【24h】

Multi-Scale Local Context Embedding for LiDAR Point Cloud Classification

机译：LIDAR点云分类的多尺度本地上下文嵌入

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The semantic interpretation using point clouds, especially regarding light detection and ranging (LiDAR) point cloud classification, has attracted a growing interest in the fields of photogrammetry, remote sensing, and computer vision. In this letter, we aim at tackling a general and typical feature learning problem in 3-D point cloud classification- how to represent geometric features by structurally considering a point and its surroundings in a more effective and discriminative fashion? Recently, enormous efforts have been made to design the geometric features, yet it is less investigated to fully explore the potentials of the features. For that, there have been many filter-based studies proposed by selecting a subset of the whole feature space for better representing the local geometry structure. However, such a hard-threshold selection strategy inevitably suffers from information loss. In addition, the construction of the geometric features is relatively sensitive to the size of the neighborhood. To this end, we propose to extract multi-scaled feature representations and locally embed them into a low-dimensional and robust subspace where a more compact representation with the intrinsic structure preservation of the data is expected to be obtained, thereby further yielding a better classification performance. In our case, we apply a popular manifold learning approach, that is, locality-preserving projections, for the task of learning low-dimensional embedding. Experimental results conducted on one LiDAR point cloud data set provided by the 2018 IEEE Data Fusion Contest demonstrate the effectiveness of the proposed method in comparison with several commonly used state-of-the-art baselines.
机译：使用点云的语义解释，特别是关于光检测和测距（LIDAR）点云分类，它引起了对摄影测量，遥感和计算机视觉领域的越来越感兴趣。在这封信中，我们的目的是在三维点云分类中解决一般和典型的特征学习问题 - 如何通过以更有效和辨别的方式在结构上考虑一个点及其周围环境来表示几何特征？最近，已经进行了巨大的努力来设计几何特征，但它较少被调查，以完全探索功能的潜力。为此，通过选择整个特征空间的子集提出了许多基于滤波器的研究，以便更好地代表局部几何结构。然而，这种硬阈值选择策略不可避免地遭受信息损失。另外，几何特征的结构对附近的尺寸相对敏感。为此，我们建议提取多尺度特征表示，并将其本地嵌入到低维和鲁棒子空间中，其中预计将获得与数据的内在结构保存的更紧凑的表示，从而进一步产生更好的分类表现。在我们的案例中，我们应用了一种流行的歧管学习方法，即，用于学习低维嵌入的任务的位置保留投影。在2018 IEEE数据融合赛提供的一个LIDAR点云数据集上进行的实验结果证明了与几种常用的最先进的基线相比的提出方法的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号