Seam image processing is the basis of the realization of automatic laser vision seam tracking system, and it has become one of the important research directions. Adding windows processing, gray processing, fast median...Seam image processing is the basis of the realization of automatic laser vision seam tracking system, and it has become one of the important research directions. Adding windows processing, gray processing, fast median filtering, binary processing and image edge extraction are used to pretreat the seam image. In the post-processing of seam image, the feature points of the target image are succesfully detected by using center line extraction and feature points detection algorithm based on slope analysis. The whole processing time is less than 150 ms, and the real-time processing of seam image can be implemented.展开更多
针对同步定位与建图(simultaneous localization and mapping,SLAM)在户外环境中定位与建图鲁棒性、准确性不足的问题,提出了一种基于半直接法的高度激光里程计(height laser odometer based on semi-direct method,SLO)。与现有的激光...针对同步定位与建图(simultaneous localization and mapping,SLAM)在户外环境中定位与建图鲁棒性、准确性不足的问题,提出了一种基于半直接法的高度激光里程计(height laser odometer based on semi-direct method,SLO)。与现有的激光里程计算法相比,该方法避免了三维点云的显式计算,主动对三维点进行降维处理生成图片,避免了三角测量误差和单目视觉SLAM中的尺度不确定性和尺度漂移问题。在高度图的基础上结合了直接方法和间接方法,使得系统在使用迭代最近点算法(iterative closest point,ICP)进行帧间匹配时更稳定、更轻便并且计算量小。高度图的使用弥补了直接方法的灰度不变性假设的缺点,并减少了照明的影响。在KITTI数据集和井下作业自动导向车(automated guided vehicle,AGV)平台上的实验结果表明,本文提出的方法有较高的鲁棒性与准确性。展开更多
为了提高激光点云的配准精度和效率,解决两片点云之间存在尺度变换的配准问题,提出了一种基于有向包围盒的尺度点云配准算法。首先,分别生成两片点云的空间有向包围盒,利用两个包围盒对应边的比值计算尺度因子。然后,将目标点云包围盒...为了提高激光点云的配准精度和效率,解决两片点云之间存在尺度变换的配准问题,提出了一种基于有向包围盒的尺度点云配准算法。首先,分别生成两片点云的空间有向包围盒,利用两个包围盒对应边的比值计算尺度因子。然后,将目标点云包围盒进行尺度放缩,再利用包围盒对应顶点的关系计算旋转矩阵。同时,引入点云的单位向量和,以单位向量和之间余弦相似度最大为准则,选择正确的旋转矩阵。最后,为了实现精确配准,将尺度因子引入点到面迭代最近点(Iterative Closest Point, ICP)算法中,利用加权最小二乘法求解变换参数。实验结果表明,在点云之间存在数据缺失、噪声干扰和尺度变换的情况下,所提算法可以实现快速精确配准,且具备良好的稳健性。展开更多
基金The work was supported by National Natural Science Foundation of China （No. 50975195）.
文摘Seam image processing is the basis of the realization of automatic laser vision seam tracking system, and it has become one of the important research directions. Adding windows processing, gray processing, fast median filtering, binary processing and image edge extraction are used to pretreat the seam image. In the post-processing of seam image, the feature points of the target image are succesfully detected by using center line extraction and feature points detection algorithm based on slope analysis. The whole processing time is less than 150 ms, and the real-time processing of seam image can be implemented.
文摘针对同步定位与建图(simultaneous localization and mapping,SLAM)在户外环境中定位与建图鲁棒性、准确性不足的问题,提出了一种基于半直接法的高度激光里程计(height laser odometer based on semi-direct method,SLO)。与现有的激光里程计算法相比,该方法避免了三维点云的显式计算,主动对三维点进行降维处理生成图片,避免了三角测量误差和单目视觉SLAM中的尺度不确定性和尺度漂移问题。在高度图的基础上结合了直接方法和间接方法,使得系统在使用迭代最近点算法(iterative closest point,ICP)进行帧间匹配时更稳定、更轻便并且计算量小。高度图的使用弥补了直接方法的灰度不变性假设的缺点,并减少了照明的影响。在KITTI数据集和井下作业自动导向车(automated guided vehicle,AGV)平台上的实验结果表明,本文提出的方法有较高的鲁棒性与准确性。
文摘为了提高激光点云的配准精度和效率,解决两片点云之间存在尺度变换的配准问题,提出了一种基于有向包围盒的尺度点云配准算法。首先,分别生成两片点云的空间有向包围盒,利用两个包围盒对应边的比值计算尺度因子。然后,将目标点云包围盒进行尺度放缩,再利用包围盒对应顶点的关系计算旋转矩阵。同时,引入点云的单位向量和,以单位向量和之间余弦相似度最大为准则,选择正确的旋转矩阵。最后,为了实现精确配准,将尺度因子引入点到面迭代最近点(Iterative Closest Point, ICP)算法中,利用加权最小二乘法求解变换参数。实验结果表明,在点云之间存在数据缺失、噪声干扰和尺度变换的情况下,所提算法可以实现快速精确配准,且具备良好的稳健性。
