为提高ORB-SLAM2 (oriented fast and rotated brief, and simultaneous localization and mapping)系统的位姿估计精度并解决仅能生成稀疏地图的问题,提出了融合迭代最近点拟合(iterative closest point, ICP)算法与曼哈顿世界假说的...为提高ORB-SLAM2 (oriented fast and rotated brief, and simultaneous localization and mapping)系统的位姿估计精度并解决仅能生成稀疏地图的问题,提出了融合迭代最近点拟合(iterative closest point, ICP)算法与曼哈顿世界假说的位姿估计策略并在系统中加入稠密建图线程。首先通过ORB(oriented fast and rotated brief)特征点法、最小显著性差异(least-significant difference, LSD)算法和聚集层次聚类(agglomerative hierarchical clustering, AHC)方法提取点、线、面特征,其中点、线特征与上一帧匹配,面特征在全局地图匹配。然后采用基于surfel的稠密建图策略将图像划分为非平面与平面区域,非平面采用ICP算法计算位姿,平面则通过面与面的正交关系确定曼哈顿世界从而使用不同估计策略,其中曼哈顿世界场景通过位姿解耦实现基于曼哈顿帧观测的无漂移旋转估计,而该场景的平移以及非曼哈顿世界场景的位姿采用追踪的点、线、面特征进行估计和优化;最后根据关键帧和相应位姿实现稠密建图。采用慕尼黑工业大学(technische universit?t münchen, TUM)数据集验证所提建图方法,经过与ORB-SLAM2算法比较,均方根误差平均减少0.24 cm,平均定位精度提高7.17%,验证了所提方法进行稠密建图的可行性和有效性。展开更多
The phenomenology of space is linked to the body experience, where the situatedness(Befindlichheit) plays the fundamental attribute of existence, and space becomes a structural element of meaning construction, while t...The phenomenology of space is linked to the body experience, where the situatedness(Befindlichheit) plays the fundamental attribute of existence, and space becomes a structural element of meaning construction, while the space itself is constructed and extended by way of intersubjectivity or Mitsein in this process. The phenomenology of space, which is portrayed through embodiment, situatedness, meaning construction, and Mitsein, poses a new requirement for the writing of the history of philosophy in the age of globalization, which is to break the Western-centric perspective and to discuss the pluralistic philosophy based on the differences of the spatial experience. By redrawing the map of world philosophy in an intercultural perspective, the pluralistic philosophical traditions can establish the new selfunderstandings and self-positionings, in order to respect the diversity of human civilization, to unite the common values of all mankind, and to build a human community with a shared future.展开更多
文摘为提高ORB-SLAM2 (oriented fast and rotated brief, and simultaneous localization and mapping)系统的位姿估计精度并解决仅能生成稀疏地图的问题,提出了融合迭代最近点拟合(iterative closest point, ICP)算法与曼哈顿世界假说的位姿估计策略并在系统中加入稠密建图线程。首先通过ORB(oriented fast and rotated brief)特征点法、最小显著性差异(least-significant difference, LSD)算法和聚集层次聚类(agglomerative hierarchical clustering, AHC)方法提取点、线、面特征,其中点、线特征与上一帧匹配,面特征在全局地图匹配。然后采用基于surfel的稠密建图策略将图像划分为非平面与平面区域,非平面采用ICP算法计算位姿,平面则通过面与面的正交关系确定曼哈顿世界从而使用不同估计策略,其中曼哈顿世界场景通过位姿解耦实现基于曼哈顿帧观测的无漂移旋转估计,而该场景的平移以及非曼哈顿世界场景的位姿采用追踪的点、线、面特征进行估计和优化;最后根据关键帧和相应位姿实现稠密建图。采用慕尼黑工业大学(technische universit?t münchen, TUM)数据集验证所提建图方法,经过与ORB-SLAM2算法比较,均方根误差平均减少0.24 cm,平均定位精度提高7.17%,验证了所提方法进行稠密建图的可行性和有效性。
文摘The phenomenology of space is linked to the body experience, where the situatedness(Befindlichheit) plays the fundamental attribute of existence, and space becomes a structural element of meaning construction, while the space itself is constructed and extended by way of intersubjectivity or Mitsein in this process. The phenomenology of space, which is portrayed through embodiment, situatedness, meaning construction, and Mitsein, poses a new requirement for the writing of the history of philosophy in the age of globalization, which is to break the Western-centric perspective and to discuss the pluralistic philosophy based on the differences of the spatial experience. By redrawing the map of world philosophy in an intercultural perspective, the pluralistic philosophical traditions can establish the new selfunderstandings and self-positionings, in order to respect the diversity of human civilization, to unite the common values of all mankind, and to build a human community with a shared future.
