Aiming at the lack of detailed comparison of existing airborne LiDAR point cloud filtering algo-rithms,a surface subsidence area in a western mining area was selected as the experimental area.Three classic algo-rithms,namely progressive morphological filtering,triangular network progressive encryption filtering,and slope threshold filtering,were selected for denoising,and the applicability of the algorithms was analyzed.The experimental results show that in the mining area of northern Shaanxi,where the surface fluctuation is obvious and the vegetation is sparse,the point cloud modeling effect after denoising is the best by using triangulation progressive morphological filtering.The test results can provide important technical means for fine modeling of mining subsidence in mining ar-eas.
Indoor navigation, indoor robotics, and other deep applications of interior space can be realized through semantic segmentation of 3D point clouds. We propose a semantic segmentation method for point clouds that uses geometric features of point clouds and neural networks to address the problem of incomplete and inconsistent segmentation objectives in existing semantic segmentation methods. Using neural networks, semantic labels are extracted from indoor structural information as the first step. The paper proposes a probabilistic model to cross-validate the initial segmentation results with the segmentation results of geometric features to achieve joint optimization of the results for semantic segmentation. Three sets of indoor point clouds data from simple to complex indoor scenes are used to test the accuracy and validity of the segmentation method proposed in this paper. The experimental results demonstrate that the method proposed in this paper can effectively improve the semantic segmentation accuracy of indoor 3D point clouds.
阴影是山区高分航空影像严重的干扰因素,去除山体阴影有助于提高实景三维建设、林业调查、变化检测等应用的准确性和有效性.本文构建了高分航空遥感影像的山体阴影指数(MSI),并提出了基于色彩迁移和色彩均衡的阴影去除方法.采用覆盖山区的0.2 m航空影像进行试验,结果表明,MSI和阈值分割法可以有效地检测航空影像的山体阴影,而结合对象化色彩迁移和基于邻域的非线性色彩均衡的阴影去除法既能有效地消除山体阴影,又能使阴影区域恢复纹理细节,色彩更贴合于非阴影区域,达到影像整体色彩更加均衡的效果.分析阴影去除前后的统计指标发现,随着阴影的去除,各波段平均值和标准差都明显增加,说明阴影区域的亮度有提高且色彩层次更加丰富.
结合Sentinel-2影像及其他高分辨率卫星数据进行长序列、高频次、大范围的水面率、蓄水量、生态流量等水资源要素监测具有重要意义.为了提高水体提取精度,解决利用多源中高分辨率卫星数据提取水体时的空间尺度效应问题,本文提出了一种面向Sentinel-2影像的亚像元级水体提取方法(简称SWES).首先利用RWI提取纯水体像元,然后利用膨胀算法提取水陆边界混合像元,最后为解决地物的类内光谱变化问题,采用考虑空间信息的多端元光谱混合分析算法(MESMA)求解水陆混合像元中的水体丰度.3个试验区的结果均表明,SWES取得了较好效果,平均RMSE为0.147,水体提取效果均优于自动亚像元水体提取方法(简称ASWM),尤其在水陆混合像元较多的坑塘养殖区.SWES在试验区获取的水体面积也有较高精度,平均相对误差为8.03％,低于ASWM的20.23％,结果表明SWES能够有效提升水域面积提取精度.
为了满足停车场快速建图的需求,本文提出了基于手持激光点云的室内停车场地面标识要素的提取方法.首先,为减少要素提取对内存空间的需求,将整个点云以规则网格进行划分;其次采用RANSAC平面拟合的方法提取每个网格内的地面点云;然后为提取地面标识要素,根据地面点云生成地面图像,并在地面图像的基础上,采用BiSeNet网络对不同的标识要素进行语义分割,得到车道线、车位线和导向箭头标识的像素;最后针对车道线和车位线,采用基于霍夫变换的直线提取方法对其进行提取,对于地面导线箭头,采用模板匹配的方法对其进行提取.试验证明,本文提出的方法能够对扫描的结构要素和标识要素进行快速提取,可大大减少制图的人工工作量,有效提高室内停车场建图的效率.
