Open sunwonlikeyou opened 3 years ago
@sunwonlikeyou There are mistakes in your code. Just fix like this: kpts = np.concatenate((keypoints_3d, dummy), axis=1) # [25, 4] kpts = np.matmul(projection[0], kpts.T).T # [3, 4] x [4, 25] --> [3, 25] --> [25, 3] kpts = kpts[:,:2]/kpts[:,2].reshape(-1,1)
I want to see 2D keypoints of certain frame on images so i did projection processing. but i got wrong result. what's the matter?? As i know about getting 2D points is {2D keypoints = homogeneous(projection matrix * 3D keypoints)} Could you tell me what's the problem...?? More details about my code: i want to see image0000000.jpg & projected 2D keypoints each frame.