gemsketch交互式图像引导点几何提取.pdfVIP

GemSketch: In ctive Image-Guided Geometry Extraction from Point Clouds 1 1 2 2 Mehran Maghoumi , Joseph J. LaViola Jr. , Karthik Desingh and Odest Chadwicke Jenkins — We introduce an in ctive system for extracting the geometries of generalized cylinders and cuboids from single- or multiple-view point clouds. Our proposed method is intuitive and only requires the object’s silhouettes to be traced by the user. Leveraging the user’s perceptual understanding of what an object looks like, our proposed method is capable of extracting accurate models, even in the presence of occlusion, clutter or plete point cloud data, while preserving the original object’s details and scale. We demonstrate the merits of our proposed method through a set of experiments on a public RGB- D dataset. We extracted 16 objects from the dataset using at most two views of each object. Our extracted models represent a high degree of visual similarity to the original objects. Further, we achieved a mean normalized Hausdorff distance of 5.66% when comparing our extracted models with the dataset’s ground truths. I. INTRODUCTION Recent advancements in the field of robotic research are propelled by 3D sensors and their ability to provide accurate measurements which are in turn used to geometrically model the objects or the environment surrounding a robot. Methods (a) (b) (c) (d) that use su odels to aid perception fall under the category Fig. 1: Geometry extraction of and occlu