Boundary Extraction of Scattered Point Cloud with Normal Estimation Based on Improved 3RDP Algorithm

An improved three-dimensional Douglas-Peucker (3RDP) algorithm is proposed to optimize the normal estimation method and solve the problem of incomplete and inaccurate point cloud contours extracted when using an angle threshold to assess the point cloud contour through the normal estimation algorithm. First, the traditional normal estimation method is used to obtain candidate points of the boundary feature under a low threshold. And, the 3RDP algorithm is introduced to thin the candidate points. Then a method of using principal component analysis to select the base surface of the point set and finding the origin and end point in the main direction is proposed, and the point set is sorted by the minimum distance selection method. Finally, according to the distance from the point to the base surface, it is judged whether the point belongs to the point on the contour line, and the internal points are removed at the same time to extract the contour feature of the target. Experimental results show that the proposed algorithm can effectively eliminate the candidate points that do not belong to the contour line in the normal estimation method. Compared with the traditional normal estimation algorithm, the extracted object contour line is more complete and accurate.