Patent · US Active

Voxel-based feature learning network

US10970518B1 · kind B1 · utility

27Cited by
3References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 13, 2018
Grant dateApr 6, 2021
Priority date
Expiry dateDec 29, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2210/12
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A voxel feature learning network receives a raw point cloud and converts the point cloud into a sparse 4D tensor comprising three-dimensional coordinates (e.g. X, Y, and Z) for each voxel of a plurality of voxels and a fourth voxel feature dimension for each non-empty voxel. In some embodiments, convolutional mid layers further transform the 4D tensor into a high-dimensional volumetric representation of the point cloud. In some embodiments, a region proposal network identifies 3D bounding boxes of objects in the point cloud based on the high-dimensional volumetric representation. In some embodiments, the feature learning network and the region proposal network are trained end-to-end using training data comprising known ground truth bounding boxes, without requiring human intervention.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.