US Patent Issued to Siemens on Oct. 28 for "Synthetic dataset creation for object detection and classification with deep learning" (California, Massachusetts Inventors)

ALEXANDRIA, Va., Oct. 28 -- United States Patent no. 12,456,287, issued on Oct. 28, was assigned to Siemens Corp. (Washington).

"Synthetic dataset creation for object detection and classification with deep learning" was invented by Eugen Solowjow (Berkeley, Calif.), Ines Ugalde Diaz (Redwood City, Calif.), Yash Shahapurkar (Berkeley, Calif.), Juan L. Aparicio Ojea (Moraga, Calif.) and Heiko Claussen (Wayland, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method for building an object detection module uses mesh representations of objects belonging to specified object classes of interest to render images by a physics-based simulator. Each rendered image captures a simulated enviro...