The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was ...The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was discussed data based on curve recognition from points cloud is proposed. The results obtained by the new algorithm are 85 % （or even higher） consistent with that of the screen displaying method, furthermore, the new method can process SLR data automatically, which makes it possible to be used in the development of the COMPASS navigation system.展开更多
In this paper, we propose a motion planning system for bin picking using 3-D point cloud. The situation that the objects are put miscellaneously like the inside in a house is assumed. In the home, the equipment which ...In this paper, we propose a motion planning system for bin picking using 3-D point cloud. The situation that the objects are put miscellaneously like the inside in a house is assumed. In the home, the equipment which makes an object stand in line doesn’t exist. Therefore the motion planning system which considered a collision problem becomes important. In this paper, Information on the objects is measured by a laser range finder (LRF). The information is used as 3-D point cloud, and the objects are recognized by model-base. We propose search method of a grasping point for two-fingered robotic hand, and propose search method of a path to approach the grasping point without colliding with other objects.展开更多
针对复杂地理实体建模中,多模态点云数据融合处理耗时、精度偏差较大等问题,本文以南通大剧院异形建筑三维建模为例,提出一种多模态控制点辅助约束的最近点迭代算法(Multimodal Control Point Assistant-Iterative Closest Point)对点...针对复杂地理实体建模中,多模态点云数据融合处理耗时、精度偏差较大等问题,本文以南通大剧院异形建筑三维建模为例,提出一种多模态控制点辅助约束的最近点迭代算法(Multimodal Control Point Assistant-Iterative Closest Point)对点云数据进行配准,该算法能够实现复杂地理实体多模态点云数据的精确配准。通过实验对比,结果表明,与传统ICP算法、SAC-IA算法、NDT算法相比,本文算法不但能够快速实现全局收敛,而且可以满足城市级三维建模精度要求。展开更多
文摘The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was discussed data based on curve recognition from points cloud is proposed. The results obtained by the new algorithm are 85 % （or even higher） consistent with that of the screen displaying method, furthermore, the new method can process SLR data automatically, which makes it possible to be used in the development of the COMPASS navigation system.
文摘In this paper, we propose a motion planning system for bin picking using 3-D point cloud. The situation that the objects are put miscellaneously like the inside in a house is assumed. In the home, the equipment which makes an object stand in line doesn’t exist. Therefore the motion planning system which considered a collision problem becomes important. In this paper, Information on the objects is measured by a laser range finder (LRF). The information is used as 3-D point cloud, and the objects are recognized by model-base. We propose search method of a grasping point for two-fingered robotic hand, and propose search method of a path to approach the grasping point without colliding with other objects.
文摘针对复杂地理实体建模中,多模态点云数据融合处理耗时、精度偏差较大等问题,本文以南通大剧院异形建筑三维建模为例,提出一种多模态控制点辅助约束的最近点迭代算法(Multimodal Control Point Assistant-Iterative Closest Point)对点云数据进行配准,该算法能够实现复杂地理实体多模态点云数据的精确配准。通过实验对比,结果表明,与传统ICP算法、SAC-IA算法、NDT算法相比,本文算法不但能够快速实现全局收敛,而且可以满足城市级三维建模精度要求。
