Plane Segmentation(平面分割)研究综述
Plane Segmentation 平面分割 - 2) it is easy to get the obstacle coordinates through plane segmentation and clustering for the use of subsequent camera and LIDAR fusion. [1] To solve this problem, this paper proposes an improved BoxInst model for the plane segmentation in remote sensing images. [2] The recognition pipeline has 5 stages: (1) Plane segmentation, (2) Pipe detection, (3) Semantic Object-segmentation and detection, (4) Feature based Object Recognition and (5) Bayesian estimation. [3] This study revealed that the Shun I strike-slip fault zone is characterized by vertical stratification, plane segmentation, multiple evolution staging, and heterogeneity of storage control. [4] The candidate camera view range is obtained by plane segmentation. [5] NEW METHOD A novel automatic filtering algorithm based on plane segmentation was proposed to locate on-scalp MEG sensors in 3D images reconstructed from optical scanning. [6] Clearly different from previous methods resorting to plane segmentation, the key to our approach is to utilize rich semantic information directly from RGB images to extract semantic planar image regions with a deep Convolutional Neural Network (CNN). [7] The accuracy and robustness of plane segmentation using a region-growing algorithm remains an important and challenging topic for terrestrial laser scanning point clouds. [8] Plane segmentation is a basic yet important process in light detection and ranging (LiDAR) point cloud processing. [9] Aiming at real-time sorting of stacked objects, a series of algorithms are proposed, including plane segmentation and template matching with low computational load and high speed, using only depth information. [10] As one of the primary tasks of point cloud processing, plane segmentation has also drawn attention of scholars from all around the world and become a very promising research area. [11] Plane segmentation and fitting method of point clouds based on improved density clustering algorithm is put forward. [12] Besides, the performance improvement is theoretically analyzed from the perspective of hyperplane segmentation. [13]2）通过平面分割和聚类很容易得到障碍物坐标，以供后续相机和激光雷达融合使用。 [1] 针对这一问题，本文提出了一种改进的BoxInst模型，用于遥感图像的平面分割。 [2] 识别管道有 5 个阶段：（1）平面分割，（2）管道检测，（3）语义对象分割和检测，（4）基于特征的对象识别和（5）贝叶斯估计。 [3] 本研究揭示顺Ⅰ走滑断裂带具有垂向分层、平面分割、多演化阶段、储集控制非均质性等特征。 [4] 通过平面分割获得候选摄像机视野范围。 [5] 新方法 提出了一种基于平面分割的新型自动滤波算法，用于在光学扫描重建的 3D 图像中定位头皮上的 MEG 传感器。 [6] 与以往采用平面分割的方法明显不同，我们方法的关键是直接从 RGB 图像中利用丰富的语义信息，通过深度卷积神经网络 (CNN) 提取语义平面图像区域。 [7] 使用区域增长算法进行平面分割的准确性和鲁棒性对于地面激光扫描点云来说仍然是一个重要且具有挑战性的课题。 [8] 平面分割是光检测和测距（LiDAR）点云处理中一个基本但重要的过程。 [9] 针对堆叠对象的实时排序，提出了一系列算法，包括平面分割和模板匹配，计算量小，速度快，仅使用深度信息。 [10] 作为点云处理的首要任务之一，平面分割也引起了世界各国学者的关注，成为一个非常有前景的研究领域。 [11] 提出了基于改进密度聚类算法的点云平面分割与拟合方法。 [12] 此外，还从超平面分割的角度对性能提升进行了理论上的分析。 [13]
point cloud processing 点云处理
Three-dimensional (3-D) plane segmentation has been and continues to be a challenge in 3-D point cloud processing. [1]三维 (3-D) 平面分割一直是并将继续是 3-D 点云处理中的挑战。 [1]
Ground Plane Segmentation
It consists of three stages: data pre-processing, occupancy grid map construction and ground plane segmentation. [1] We formulate the problem as an inter-mingled multi-task prediction problem by jointly optimizing for pixel-wise surface normal direction, ground plane segmentation, and depth estimates. [2]它包括三个阶段：数据预处理、占用网格图构建和地平面分割。 [1] 我们通过联合优化逐像素表面法线方向、地平面分割和深度估计，将问题表述为混合多任务预测问题。 [2]
Roof Plane Segmentation 屋顶平面分割
Conventional building modeling methods often rely on successive roof plane segmentation and fitting. [1] In this article, we develop a novel region expansion based L0 gradient minimization algorithm for processing unordered point cloud data, and a two-stage global optimization method consisting of the L0 gradient minimization and graph cut for roof plane segmentation. [2]传统的建筑建模方法通常依赖于连续的屋顶平面分割和拟合。 [1] 在本文中，我们开发了一种新的基于区域扩展的 L0 梯度最小化算法来处理无序点云数据，以及一种由 L0 梯度最小化和图割组成的用于屋顶平面分割的两阶段全局优化方法。 [2]