FEATURE EXTRACTION METHOD FOR MOTION RECOGNITION IN IMAGE AND MOTION RECOGNITION METHOD USING SKELETON INFORMATION

摘要

A method for recognizing a user's motion using skeleton information includes the steps of performing a neural network learning using the motion recognition device as a first feature point based on a first plurality of joint points of a human joint point in a plurality of training motion containing training images of a person, The motion recognition device acquires a human input motion-containing input image with a camera, the motion recognition device generates a second plurality of joint points at the same position as the first plurality of joint points of the person's joint points in the input image Extracting a second feature point based on the second feature point, and inputting the second feature point to a neural network network formed through the neural network learning to determine a training operation corresponding to the input operation.;