Mateo Carlos M, Corrales Juan A, Mezouar Youcef
UMR6602 Institut Pascal (IP), Université Clermont Auvergne, SIGMA Clermont, Clermont-Ferrand, France.
Front Robot AI. 2021 Feb 18;7:600387. doi: 10.3389/frobt.2020.600387. eCollection 2020.
This paper presents a novel approach to implement hierarchical, dense and dynamic reconstruction of 3D objects based on the VDB (Variational Dynamic B + Trees) data structure for robotic applications. The scene reconstruction is done by the integration of depth-images using the Truncated Signed Distance Field (TSDF). The proposed reconstruction method is based on dynamic trees in order to provide similar reconstruction results to the current state-of-the-art methods (i.e., complete volumes, hashing voxels and hierarchical volumes) in terms of execution time but with a direct multi-level representation that remains real-time. This representation provides two major advantages: it is a hierarchical and unbounded space representation. The proposed method is optimally implemented to be used on a GPU architecture, exploiting the parallelism skills of this hardware. A series of experiments will be presented to prove the performance of this approach in a robot arm platform.
本文提出了一种基于VDB（变分动态B+树）数据结构的新颖方法，用于机器人应用中实现3D物体的分层、密集和动态重建。场景重建通过使用截断符号距离场（TSDF）对深度图像进行融合来完成。所提出的重建方法基于动态树，以便在执行时间方面提供与当前最先进方法（即完整体积、哈希体素和分层体积）相似的重建结果，但具有直接的多级表示且保持实时性。这种表示提供了两个主要优点：它是一种分层且无界的空间表示。所提出的方法经过优化，可在GPU架构上使用，利用该硬件的并行技能。将展示一系列实验，以证明该方法在机器人手臂平台上的性能。
