RANSAC平面估计算法在路面物体体积测量中的应用  

Application of Plane Estimation Algorithm Based on RANSAC in Volume Measurement of Object on Road Surface

作　　者：曹毓[1] 冯莹[1] 杨云涛[1] 陈晗[1] 

机构地区：[1]国防科学技术大学光电科学与工程学院,长沙410073

出　　处：《传感技术学报》2012年第3期413-416,共4页Chinese Journal of Sensors and Actuators

基　　金：总后勤部预研项目

摘　　要：在利用车载单线式激光扫描仪实施路面三维重建及路面目标物体积测量的应用中,使用RANSAC平面估计算法获得了路面的0高度平面,提高了路面目标物体积计算的精度。实际测试表明,对路面上一不规则形状坑,采用注水法测量得到的坑体积为2.25 m3,点云经优化前后计算得到的坑体积分别为1.86 m3和2.10 m3,误差分别为17.3%和6.7%,点云优化过程耗时约7 s。因此,本文的路面三维点云优化方法速度快,且三维重建效果及目标物的体积计算精度可满足实际要求。In the application of the road surface 3D reconstruction and object volume measurment by vehicle-borne laser scanner, the zero-hight plane of the road can obtained by the plane estimation algorithm based on RANSAC, and the accuracy of volume measurement of object on road surface is high. Experiment result showed that, the volume of an irregular crater on the road which is measured by water flooding method is 2.25 m^3. The volume is 1.86 m^3 and 2. 10 m^3 respectively before and after the points cloud optimization with the error of 17.3% and 6.7%, and the optimization time is around 7 s. Therefore, the points cloud optimization method on road surface proposed on this paper has the advantage of high-speed calculation. Meanwhile the volume accuracy and the 3D re- construction effect could meet the requirement in practice.

关 键 词：体积测量 点云优化 RANSAC算法 路面三维重建 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置]