基于自适应颜色和几何混合特征的点云配准方法

Point Cloud Registration Method Based on an Adaptive Mixed Features of Color and Geometry

针对三维点云配准问题,文章提出了一种基于颜色和几何特征直方图自适应的混合特征配准方法。首先,通过颜色直方图对源点云模型的颜色信息进行统计,在一定颜色容差内筛选出两片点云共有颜色的数据,构建候选点集;然后将颜色特征直方图的"色"和几何特征直方图的"形"有机结合,设定两种特征自适应比例进行加权组合进行特征点提取,有效提高了点云配准的速度和精确性。实验结果表明,基于自适应颜色和几何混合特征提取特征点进行配准的方法与基于颜色和几何特征的6DICP方法相比,该种方法缩短了配准时间,配准效果稳定。实验验证了选取的基于自适应混合特征权重为最优取值。

Aiming at the problem of 3 D point cloud registration,this paper proposes a registration method based on the mixed features of histograms of color and geometric features.Firstly,the method uses the color histogram method to count the color information of the source point cloud model,and within a certain color tolerance,selects two pieces of point cloud with the same color data to construct a candidate point set.Then,the"color"of the color feature histogram and the"shape"of the geometric feature histogram are combined organically,and the mixing ratio of the two features is set.The weighted combination is mixed into the three-dimensional point cloud registration to effectively improve the speed and accuracy of the point cloud registration.The experimental results show that the method of extracting features by color and geometric feature histograms,compared with the 6 DICP method based on color and geometric features,shortens the registration time and its registration effect is stable.And the enperiment verifies that the selected adaptive hybrid feature weight is the optimal value.