LEARNING METHOD AND LEARNING DEVICE FOR REMOVING JITTERING ON VIDEO ACQUIRED THROUGH SHAKING CAMERA BY USING A PLURALITY OF NEURAL NETWORKS FOR FAULT TOLERANCE AND FLUCTUATION ROBUSTNESS IN EXTREME SITUATIONS AND TESTING METHOD AND TESTING DEVICE USING THE SAME

摘要

Support in video generated by camera shake to remove jitter on video using Neural Network, provided for Fault Tolerance and Fluctuation Robustness in extreme conditions. A method of detecting turing, comprising: generating, by a computing device, each t-th mask corresponding to each object in the t-th image; For each t-th mask, each t-th cropped image, each t-1th mask, and each t-1th cropped image, a second neural network operation is applied at least once to obtain the tth Generating each t-th object motion vector of each object pixel included in the image; And generating each t-th jittering vector corresponding to each reference pixel among pixels in the t-th image by referring to each t-th object motion vector, wherein the present invention comprises: It can be used for video stabilization, ultra-precision object tracking, behavior prediction, and motion decomposition.