This work is based on our paper Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Welding (https://ieeexplore.ieee.org/abstract/document/8593910). In this paper we show how point cloud based perception can push state-of-the-art in robotic welding. We propose novel methods for edge and corner detection in unorganized point clouds, that can be used for automatic weld seam detection directly from a point cloud. This method proposes a flexible online detection method as opposed to offline planning of welding paths.
In this repository, we release code and data for edge and corner detection for unorganized point clouds.