一种改进的KinectFusion三维重构算法  

An Improved KinectFusion 3D Reconstruction Algorithm

作　　者：朱笑笑[1] 曹其新[1] 杨扬[1] 陈培华[1] 

机构地区：[1]上海交通大学机器人研究所机械系统与振动国家重点实验室,上海200240

出　　处：《机器人》2014年第2期129-136,共8页Robot

基　　金：国际热核聚变实验堆(ITER)计划专项资助项目(2011GB113005)

摘　　要：对KinectFusion算法进行了两个方面的改进,一方面提出使用环境中的边线特征点匹配来提高其定位鲁棒性,另一方面在点云模型中预设一个地面点云来降低累积误差提高精度.在一个RGB-D(颜色-深度)SLAM验证数据集以及一个实验室的场景数据上进行了建模对比实验,结果显示,改进后的算法在鲁棒性和精度上均有明显提高,在建立一个尺度为6m×3m×3m的环境时建模误差由4.5%降低为1.5%.虽然算法运行的效率有所下降但仍保持较高实时性,对建模时的用户体验没有明显影响.Two improvements of KinectFusion algorithm are proposed. On one hand, the edge feature points in the environment are matched to improve the robustness, on the other hand, a ground plane point cloud in the model is preset to improve the accuracy. A standard RGB-D （RGB-Depth） SLAM （simultaneous localization and mapping） benchmark dataset and a data of the lab environment are modeled, and the comparison results show that, both the robustness and the accuracy are improved obviously after the improvement. The improved algorithm decreases the modeling error from 4.5% to 1.5% in a room of 6m × 3 m × 3 m. Although the efficiency is influenced, the running speed of the algorithm is still very high, and the user experience during modeling is good.

关 键 词：KinectFusion算法 同时定位与地图创建 Kinect传感器 密集重建 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]