Efficient Hough Transform for Automatic Detection of Cylinders in Point Clouds

We present an efficient Hough transform for automatic detection of cylinders in point clouds. As cylinders are one of the most frequently used primitives for industrial design, automatic and robust methods for their detection and fitting are essential for reverse engineering from point clouds. The current methods employ automatic segmentation followed by geometric fitting, which requires a lot of manual interaction during modelling. Although Hough transform can be used for automatic detection of cylinders, the required 5D Hough space has a prohibitively high time and space complexity for most practical applications. We address this problem in this paper and present a sequential Hough transform for automatic detection of cylinders in point clouds. Our algorithm consists of two sequential steps of low dimensional Hough transforms. The first step, called Orientation Estimation, uses the Gaussian sphere of the input data and performs a 2D Hough Transform for finding strong hypotheses for the direction of cylinder axis. The second step of Position and Radius Estimation, consists of a 3D Hough transform for estimating cylinder position and radius. This sequential breakdown reduces the space and time complexity while retaining the advantages of robustness against outliers and multiple instances. The results of applying this algorithm to real data sets from two industrial sites are presented that demonstrate the effectiveness of this procedure for automatic cylinder detection.