基于空间投影点云分割的序列图像三维重建  

3D sequence image reconstruction based on spatial projection point cloud segmentation

作　　者：陈瑞林 郑宇 张晓燕 廖加铭 CHEN Ruilin;ZHENG Yu;ZHANG Xiaoyan;LIAO Jiaming(School of Information Science and Technology,Jiageng College,Xiamen University,Zhangzhou,Fujian 363105,China)

机构地区：[1]厦门大学嘉庚学院信息科学与技术学院,福建漳州363105

出　　处：《信息记录材料》2022年第9期24-27,共4页Information Recording Materials

基　　金：福建省自然基金(2020J01039);漳州市科技计划项目(ZZ2020J04);厦门大学嘉庚学院大学生创新创业计划项目(202213469304)(202213469115)。

摘　　要：提出了一种基于空间投影的点云分割重建算法。首先在靶标世界坐标系中实现空间投影的点云分割,获取到所需的点云数据,之后利用光线投射算法将2D点反向投影到三维空间中,再将3D点投影到RGB图像中创建点云,最后再使用改进的ICP算法进行点云拼接得到最终结果。通过对比分析,验证了算法的有效性。This paper presents a point cloud segmentation and reconstruction algorithm based on spatial projection.Firstly,the point cloud is segmented in the world coordinate system of the target,and the needed point cloud data are obtained.Then,the 2D points are projected back into the 3D using the ray-casting algorithm,then point clouds are created by projecting 3D points into RGB images,and finally point clouds are stitched using improved ICP algorithm to get the final results.The effectiveness of the algorithm is verified by comparative analysis.

关 键 词：深度图像 光线投影 三维重建 ICP算法 

分 类 号：TP279[自动化与计算机技术—检测技术与自动化装置]