欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对移动服务机器人在未知室内环境下的三维感知问题,提出了一种基于低成本Kinect传感器的三维地图创建实用方法.对于机器人在运动过程中连续采集的多帧RGB-D信息,首先利用SURF算子对RGB图像提取稳定特征点并进行特征点匹配,然后结合深度图像,采用RANSAC算法剔除可能存在的误匹配点并完成初始配准,从而估计得到图像帧间粗略的相对转移关系,最后运用广义ICP算法对采集的深度图像进行精确配准,得到拼接的三维点云图.在此基础上进一步开发了移动机器人三维地图创建应用系统,实验验证了该方法的可行性和有效性.
英文摘要：
For the 3D perception problem of mobile service robots in unknown indoor environments,a practical approach to building 3D maps using a low-cost Kinect sensor is proposed.Successive frames of RGB-D（red-green-blue-depth） information are captured during the robot＇s movements.First,SURF（speeded up robust features） detector is applied to color images for extracting and matching stable feature points.Combined w ith depth images,initial registration procedure is then performed by using the RANSAC（random sample consensus） algorithm for eliminating possible mistake matching points and thus the relative transformation betw een frames can be estimated.Finally,a generalized ICP（iterative closest point） algorithm is employed to perform fine registration on captured depth images,w hich finally produces 3D point cloud mosaic.In addition,an application system of mobile robot 3D mapping is developed.Experimental results validate the practicability and effectiveness of the approach.
同期刊论文项目
同项目期刊论文
An Interactive Visual Navigation Method Using a Hand-drawn-Route-Map in an Unknown Dynamic Environme
Spatial-temporal Collaborative Sequential Monte Carlo for Mobile Robot Localization in Distributed I
Decision-Theoretical Navigation of Service Robots Using POMDPs with Human-Robot Co-Occurrence Predic
期刊信息
位置：