The estimation and refinement of pose of joints in human picture using cascade stages of multiple convolutional neural networks

摘要

The present invention relates to a method for predicting joint coordinates in an image. More specifically, the present invention relates to the method for predicting joint coordinates in an image using multiple convolutional neural networks. The method predicts the joint coordinates of a person in a human image in advance and predicts the joint coordinates again in a partial image including the predicted joint coordinates so as to greatly increase accuracy of prediction.