US Patent Issued to NVIDIA on July 7 for "Data augmentation for model training" (American, Canadian Inventors)

ALEXANDRIA, Va., July 7 -- United States Patent no. 12,675,945, issued on July 7, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Data augmentation for model training" was invented by Malik Aqeel Anwar (Atlanta), Tae Eun Choe (Belmont, Calif.), Zian Wang (Toronto), Sanja Fidler (Toronto) and Minwoo Park (Santa Clara, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "In various examples, systems and methods are disclosed that relate to data augmentation for training/updating perception models in autonomous or semi-autonomous systems and applications. For example, a system may receive data associated with a set of frames that are captured using a plurality of cameras positioned in fixed relation relat...