Next best view (NBV) planning is a central task for automated three-dimensional (3-D) reconstruction in robotics. The most expensive phase of NBV computation is the view simulation step, where the information gain of a large number of candidate sensor poses are estimated. Usually, information gain is related to the visibility of unknown space from the simulated viewpoint. A well-established technique is to adopt a volumetric representation of the environment and to compute the NBV from ray casting by maximizing the number of unknown visible voxels. This letter explores a novel approach for NBV planning based on surfel representation of the environment. Surfels are oriented surface elements, such as circular disks, without explicit connectivity. A new kind of surfel is introduced to represent the frontier between empty and unknown space. Surfels are extracted during 3-D reconstruction, with minimal overhead, from a KinectFusion volumetric representation. Surfel rendering is used to generate images from each simulated sensor pose. Experiments in a real robot setup are reported. The proposed approach achieves better performance than volumetric algorithms based on ray casting implemented on graphics processing unit (GPU), with comparable results in terms of reconstruction quality. Moreover, surfel-based NBV planning can be applied in larger environments as a volumetric representation is limited by GPU memory.
Surfel-Based Next Best View Planning
2018-01-01
Article (Journal)
Electronic Resource
English
DDC: | 629 |