US Patent Issued to TOYOTA RESEARCH INSTITUTE on Dec. 2 for "End-to-end monocular 2D semantic keypoint detector and tracker learning" (California Inventors)

ALEXANDRIA, Va., Dec. 2 -- United States Patent no. 12,488,597, issued on Dec. 2, was assigned to TOYOTA RESEARCH INSTITUTE INC. (Los Altos, Calif.).

"End-to-end monocular 2D semantic keypoint detector and tracker learning" was invented by Kuan-Hui Lee (San Jose, Calif.), Kun-Hsin Chen (Mountain View, Calif.), Haofeng Chen (Stanford, Calif.), Arjun Bhargava (San Francisco) and Sudeep Pillai (Santa Clara, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for semantic keypoint detection is described. The method includes linking, using a keypoint graph neural network (KGNN), semantic keypoints of an object within a first image of a video stream into a 2D graph structure corresponding to a category ...