Feature initialization is an important issue in the monocular simultaneous locahzation ana mapping （SLAM） literature as the feature depth can not be obtained at one observation. In this paper, we present a new featu...Feature initialization is an important issue in the monocular simultaneous locahzation ana mapping （SLAM） literature as the feature depth can not be obtained at one observation. In this paper, we present a new feature initialization method named modified homogeneous parameterization （MHP）, which allows undelayed initialization with scale invariant representation of point features located at various depths. The linearization error of the measurement equation is quantified using a depth estimation model and the feature initialization process is described. In order to verify the performance of the proposed method, the simulation is carried out. Results show that with the proposed method, the SLAM algorithm can achieve better consistency as compared with the existing inverse depth parameterization （IDP） method.展开更多
构建更详细的地图以及估计更精准的相机位姿一直都是同时定位与地图构建(Simultaneous Localization And Mapping,SLAM)技术所追求的目标,但是以上目标与实时性要求、较低的计算代价和受限的计算资源条件是相矛盾的。提出一种在单目ORB-...构建更详细的地图以及估计更精准的相机位姿一直都是同时定位与地图构建(Simultaneous Localization And Mapping,SLAM)技术所追求的目标,但是以上目标与实时性要求、较低的计算代价和受限的计算资源条件是相矛盾的。提出一种在单目ORB-SLAM(Oriented FAST and Rotated BRIEF-SLAM)方法的基础上利用关键帧中提取到的直线特征进行半稠密三维重建的方法。由ORB-SLAM实时提供一组关键帧及其对应的相机位姿信息和一系列地图点,提出一种关键帧再剔除算法进一步减少冗余帧数目,使用直线段提取方法提取各帧中的直线段,使用纯几何约束方法对以上检测得到的直线段进行匹配,生成一个由直线段构成的半稠密三维场景模型。实验结果表明新方法持续稳定的运行,能在低计算代价条件下快速地在线三维重建。展开更多
文摘Feature initialization is an important issue in the monocular simultaneous locahzation ana mapping （SLAM） literature as the feature depth can not be obtained at one observation. In this paper, we present a new feature initialization method named modified homogeneous parameterization （MHP）, which allows undelayed initialization with scale invariant representation of point features located at various depths. The linearization error of the measurement equation is quantified using a depth estimation model and the feature initialization process is described. In order to verify the performance of the proposed method, the simulation is carried out. Results show that with the proposed method, the SLAM algorithm can achieve better consistency as compared with the existing inverse depth parameterization （IDP） method.
文摘构建更详细的地图以及估计更精准的相机位姿一直都是同时定位与地图构建(Simultaneous Localization And Mapping,SLAM)技术所追求的目标,但是以上目标与实时性要求、较低的计算代价和受限的计算资源条件是相矛盾的。提出一种在单目ORB-SLAM(Oriented FAST and Rotated BRIEF-SLAM)方法的基础上利用关键帧中提取到的直线特征进行半稠密三维重建的方法。由ORB-SLAM实时提供一组关键帧及其对应的相机位姿信息和一系列地图点,提出一种关键帧再剔除算法进一步减少冗余帧数目,使用直线段提取方法提取各帧中的直线段,使用纯几何约束方法对以上检测得到的直线段进行匹配,生成一个由直线段构成的半稠密三维场景模型。实验结果表明新方法持续稳定的运行,能在低计算代价条件下快速地在线三维重建。
