融合梯度信息和邻域点云分布的3D线特征提取与配准

Extraction and registration of 3D lines by fusing gradient information and neighboring point cloud distribution

针对传统点云场景重建中由于场景区域缺乏纹理、场景物体遮挡等导致重建结果不准确的局限性,借助场景包含的几何特性和线结构信息,有效利用RGB-D数据的梯度信息和邻域点云分布信息,本文提出了一种针对点云场景的3D线特征提取、匹配和配准方法.首先,通过场景RGB图的梯度信息确定梯度方向相似的3D直线段支持域.然后,借助场景深度图呈现的邻域几何特性,根据当前点与其邻近点之间的分布关系判断点云中的直线型边界线点云和直线型折边线点云并拟合得到场景3D线特征.其次,以点云场景提取的3D线特征为轴线,构造等厚度同轴圆柱区域作为3D线段支持域,并统计支持域中各层圆柱壁内点云梯度作为描述符实现3D线特征匹配.最后,利用基于线–线的迭代最近线配准算法,迭代计算得到帧间场景的旋转与平移,从而实现帧间点云场景的高效配准.实验结果表明,与已有的点云场景线特征提取及点特征配准方法比较,本文直接基于线特征的方法配准效率高、计算量小、配准精准,方法具有较强的鲁棒性.

The traditional point-based scene reconstruction scheme always leads to inaccurate 3 D reconstruction results due to its lack of scene texture and object occlusions.With the help of geometric characteristics and line features of 3 D point cloud scenes,a novel extraction,matching,and registration method of 3 D line features is presented by fusing RGB gradients and the spatial distribution of neighboring point clouds.Firstly,the supporting region of 3 D linear segments with similar gradient directions can be determined by the gradients of an RGB scene image.Secondly,owing to the neighboring geometric features contained in the depth map,the point set of boundary lines and folded edge lines can also be extracted according to the spatial distribution of the current point and its neighboring points.The 3 D line features can thus be fitted by these extracted point sets respectively.Thirdly,taking each extracted 3 D line feature as a central axis,the supporting region can be constructed as the co-axial cylinder with the same thickness of each cylindrical layer.According to the 3 D gradient statistics of point cloud within each cylindrical layer,we can calculate an intrinsic descriptor for each 3 D line,which can be adopted to match 3 D line features between scene frames.Finally,a novel line-to-line iterative closest line registration algorithm is introduced to compute the rotation and translation transformations,and the inter-frame point cloud scene data can be registered efficiently.The experimental results illustrate that the proposed line feature-based scheme has high registration efficiency,less computational cost,accurate registration,and strong robustness when compared with the existing line feature extraction and point-based registration methods.