Plane Features(平面特征)研究综述
Plane Features 平面特征 - AutoPCD splits the PCD into multiple parts, approximates them by several 3D planes, and independently learns the plane features for reconstruction. [1] However, existing methods mainly focus on nonplanar features and do not deal well with the matching of plane features. [2] In this article, an efficient technique to classify human actions by utilizing steps like removing redundant frames from videos, extracting Segments of Interest (SoIs), feature descriptor mining through Geodesic Distance (GD), 3D Cartesian-plane Features (3D-CF), Joints MOCAP (JMOCAP) and n-way Point Trajectory Generation (nPTG). [3] To further exploit translational equivariance, convolutional neural networks are applied to process the plane features. [4] Human actions are tracked according to four features, namely, (1) geodesic distance; (2) 3D Cartesian-plane features; (3) joints Motion Capture (MOCAP) features and (4) way-points trajectory generation. [5] To reduce the strong dependence of feature matching of point-based visual simultaneous location and mapping system, besides, improve the efficiency of feature matching of line-based V-SLAM, a novel visual SLAM system named Multiple Features-SLAM by fusing the point, line segment and plane features is proposed. [6] For translation estimation in MW scenes and full camera pose estimation in non-MW scenes, we make use of point, line and plane features for robust tracking in challenging scenes. [7] This is followed by dilated 1-D convolutions across slices to aggregate in-plane features in a slice-wise manner and encode the information in the entire volume. [8] Different from geometric map-based 3-D LiDAR odometry methods with point features, we concern significant line and plane features based on eigenvalues of neighboring points. [9] This paper presents a tightly-coupled aided inertial navigation system (INS) with point and plane features, a general sensor fusion framework applicable to any visual and depth sensor (e. [10] Also off-plane features are unequally influenced by the noise level. [11] The model is applicable to investigating lifting surfaces having low to moderate sweep, dihedral, out-of-plane features such as winglets, in both steady-state and unsteady cases. [12] In this paper, we describe a feature-based approach using segmentation and clustering algorithm, which results in mathematically principled line and plane features. [13] It is supported by first-principles calculations to unravel the influence of spin-orbit coupling in the formation of the resonant exciton and to identify its in-plane and out-of-plane features. [14] ,Results obtained by applying vortex lattice methods to PrandtlPlane configuration, validated previously with wind tunnel tests, are compared to the output of a “Roskam-like” method, here defined to model the PrandtlPlane features. [15] The model is applicable to investigating lifting surfaces having low to moderate sweep, dihedral, out-of-plane features such as winglets, in both steady-state and unsteady cases. [16] First, we detect and track the point and plane features from color and depth images, and reliable constraints are obtained, even for low-texture scenes. [17] (1990), who attributed the dipping reflectors to scattering artifacts from out-of-plane features. [18] The plane features of the group space are characterized by axis extension, multi-path expansion, and layer-by-layer progression; the three-dimensional form is distinct in levels and orderly in priority; the space concept embodies the philosophical thoughts of "harmony between heaven and man" and "combination of ritual and music" and "The philosophy of "accompanying of benevolence and righteousness". [19]AutoPCD 将 PCD 拆分为多个部分，通过几个 3D 平面对它们进行逼近，并独立学习平面特征进行重建。 [1] 然而，现有的方法主要关注非平面特征，并不能很好地处理平面特征的匹配。 [2] 在本文中，一种有效的技术通过利用从视频中删除冗余帧、提取感兴趣的片段 (SoI)、通过测地距离 (GD) 挖掘特征描述符、3D 笛卡尔平面特征 (3D-CF) 等步骤对人类行为进行分类，关节 MOCAP (JMOCAP) 和 n 路点轨迹生成 (nPTG)。 [3] 为了进一步利用平移等方差，卷积神经网络被用于处理平面特征。 [4] 根据四个特征跟踪人类行为，即（1）测地距离； (2) 3D笛卡尔平面特征； (3) 关节运动捕捉 (MOCAP) 特征和 (4) 航路点轨迹生成。 [5] 为了减少基于点的视觉同步定位与建图系统对特征匹配的强依赖，同时提高基于线的V-SLAM的特征匹配效率，一种新颖的视觉SLAM系统，名为Multiple Features-SLAM，通过点融合，提出了线段和平面特征。 [6] 对于 MW 场景中的平移估计和非 MW 场景中的全相机位姿估计，我们利用点、线和平面特征在具有挑战性的场景中进行鲁棒跟踪。 [7] 接下来是跨切片的扩张一维卷积，以切片方式聚合平面内特征，并将信息编码到整个体积中。 [8] 与具有点特征的基于几何地图的 3-D LiDAR 里程计方法不同，我们关注基于相邻点特征值的重要线和平面特征。 [9] 本文提出了一种具有点和平面特征的紧耦合辅助惯性导航系统（INS），这是一种适用于任何视觉和深度传感器（例如，深度传感器）的通用传感器融合框架。 [10] 离平面特征也受噪声水平的不同影响。 [11] 该模型适用于研究在稳态和非稳态情况下具有低到中等扫掠、二面角、平面外特征（如小翼）的升力面。 [12] 在本文中，我们描述了一种使用分割和聚类算法的基于特征的方法，该方法产生具有数学原理的线和平面特征。 [13] 它得到第一性原理计算的支持，以揭示自旋轨道耦合在共振激子形成中的影响，并确定其面内和面外特征。 [14] ,通过将涡晶格方法应用于 PrandtlPlane 配置获得的结果（之前通过风洞测试验证）与“Roskam-like”方法的输出进行比较，此处定义为对 PrandtlPlane 特征进行建模。 [15] 该模型适用于研究在稳态和非稳态情况下具有低到中等扫掠、二面角、平面外特征（如小翼）的升力面。 [16] 首先，我们从颜色和深度图像中检测和跟踪点和平面特征，并获得可靠的约束，即使对于低纹理场景也是如此。 [17] (1990)，他将倾斜反射器归因于平面外特征的散射伪影。 [18] 群空间的平面特征表现为轴扩展、多路径扩展、逐层递进；立体形式层次分明，优先有序；空间理念体现了“天人合一”、“礼乐合一”的哲学思想和“仁义相伴”的哲学思想。 [19]
plane features extracted
By combing high-precision plane features extracted from point clouds and accurate boundary constraint features from oblique images, the building mainframe model, which provides an accurate reference for further editing, is quickly and automatically constructed. [1] To overcome the self-repetitive structure of indoor environments, the proposed framework uses novel description functions for both line and plane features extracted from RGB and depth images for further matching between successive RGB-D frame features. [2]通过结合点云提取的高精度平面特征和倾斜图像的精确边界约束特征，快速自动构建建筑主机模型，为后续编辑提供准确参考。 [1] 为了克服室内环境的自我重复结构，所提出的框架对从 RGB 和深度图像中提取的线和平面特征使用新颖的描述函数，以进一步匹配连续的 RGB-D 帧特征。 [2]