Hand skeleton learning, lifting, and noise removal from 2D images

摘要

The processor identifies keypoints 115, 120, 125, 130 of the hand in the two-dimensional image 100 captured by camera 215. The three-dimensional pose of the hand is determined using the location of the keypoint to access a lookup table (LUT) 230 representing the potential pose of the hand as a function of the location of the keypoint. In some embodiments, the keypoint is located at the ends of the fingers and thumb, joints connecting the knuckles of the fingers and thumb, palm knuckles indicating the point where the fingers and thumb attach to the palm, and the hand at the forearm. Wrist position indicating the point of attachment. Some embodiments of the LUT represent the 2D coordinates of the fingers and thumb in the corresponding finger pose plane.