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：
针对室内机器人移动导航定位存在的问题,该文研究了基于Kinect传感器的定位算法。该方法应用Kinect传感器采集了移动机器人运动过程中连续帧的彩色和深度信息;通过尺度不变特征变换算法匹配连续场景图像中的特征点对,经随机抽样一致性算法剔除点集中的误匹配点;利用Kinect的深度信息将可用点集的二维坐标转换到相机坐标系下的三维坐标;并使用绝对定向算法计算机器人在相邻位置上的姿态信息和平移量,从而提高了机器人的移动参数的计算精度。通过实验验证了该方法的可行性,且能够满足实时要求,可以同时进行定位与地图创建。
英文摘要：
In order to solve the navigation and positioning problem of indoor mobile robot,this paper proposed an algorithm of self-localization based on Kinect sensor.Using Kinect sensor to process the robot motion continuous frame color and depth information,SIFT algorithm to match feature points of images in a row,and RANSAC algorithm to eliminate false matching points of concentration;the depth information of Kinect was used to transform available point set of two-dimensional coordinate to the three-dimensional coordinates under camera coordinate system;absolute orientation algorithm was used to calculate the robot＇s profile information and translation on adjacent position,which improved the calculation precision of the moving parameters of robot.Experimental results indicated the feasibility of the proposed method,and it could satisfy the real-time requirement and provide prior information for simultaneous localization and mapping of robots.
同期刊论文项目
同项目期刊论文
期刊信息
位置：