Three-dimensional point cloud data subtle feature extraction algorithm for laser scanning measurement of large-scale irregular surface in reverse engineering

Abstract

In reverse engineering, feature extraction of point cloud data is a key process for the precision machining of the large-scale complex workpieces. Because of the large numbers of the point cloud data and the difficult recognition of the complex feature, incomplete feature recognition will have a serious impact on the accuracy of the machining. Thus, this paper proposes a subtle feature extraction algorithm, which can be used for the laser scanning measurement of the large-scale irregular surface. First, the L1-median point is calculated as the center point of the neighborhood. Second, the k + 1 neighbors are introduced to compute the feature description of the point cloud. Then, the feature is extracted by multi-threshold based on Poisson region growth algorithm. Last, the proposed algorithm is applied to feature extraction experiment of point cloud data for the large spherical crown workpiece. Compared with the traditional algorithms, the proposed algorithm not only can identify the subtle feature information quickly, but also can locate the weld position more accurately.