基于三维激光扫描的立体图像层次化分割方法  

Hierarchical segmentation method for stereoscopic images based on 3D laser scanning

作　　者：宗敏[1] 吴瑜 陈思雨 ZONG Min;WU Yu;CHEN Siyu(Weifang College,Weifang Shandong 261061,China)

机构地区：[1]潍坊学院,山东潍坊261061

出　　处：《激光杂志》2024年第11期128-132,共5页Laser Journal

基　　金：山东省自然科学基金(No.ZR2019PF023);潍坊学院博士基金(No.校2023002)。

摘　　要：针对现阶段立体图像层次化分割效果不佳的问题,提出基于三维激光扫描的立体图像层次化分割方法。首先,基于三维激光扫描仪采集立体图像三维激光点云数据;其次,标定立体图像像素点和三维激光点云数据的对应关系;最后,通过OTSU多阈值分割方法实现立体图像层次化分割。实验结果表明,所提方法的平均交并比在83.6%~92.5%之间,立体图像层次化分割精度高、效果好、更适合于实际应用。A hierarchical segmentation method for stereo images based on 3D laser scanning is proposed to address the current issue of poor hierarchical segmentation performance in stereo images.Firstly,based on a 3D laser scanner,collect 3D laser point cloud data from stereo images;Secondly,calibrate the correspondence between stereo image pixels and 3D laser point cloud data;Finally,hierarchical segmentation of stereo images is achieved through OTSU multi threshold segmentation method.The experimental results show that the average intersection to union ratio of the proposed method is between 83.6%and 92.5%,and the hierarchical segmentation accuracy of stereo images is high,the effect is good,and it is more suitable for practical applications.

关 键 词：激光点云数据 立体图像 层次化分割 OTSU多阈值分割方法 三维激光扫描仪 

分 类 号：TN911[电子电信—通信与信息系统]