Hi @shaozu , thanks for your share. According to kitti_development_kit/readme.txt, GT pose is left camera(Z-front, X-right, Y-down) in left_camera_0th(world) pose. when convert GT pose into loam's camera_init frame(Z-front, X-left, Y-up), use R_transform << 0, 0, 1, -1, 0, 0, 0, -1, 0;. I think R_camInit_world = Rz(-pi), p_camInit = R_camInit_world * GT_pose, should be R_transform << -1, 0, 0, 0, -1, 0, 0, 0, 1?
When publish "/velodyne_points" to loam, each points is in camera_init loam's world frame, why not is velodyne frame?
Hi @shaozu , thanks for your share. According to kitti_development_kit/readme.txt, GT pose is left camera(Z-front, X-right, Y-down) in left_camera_0th(world) pose. when convert GT pose into loam's camera_init frame(Z-front, X-left, Y-up), use R_transform << 0, 0, 1, -1, 0, 0, 0, -1, 0;. I think
R_camInit_world = Rz(-pi), p_camInit = R_camInit_world * GT_pose, should be R_transform << -1, 0, 0, 0, -1, 0, 0, 0, 1
?When publish "/velodyne_points" to loam, each points is in camera_init loam's world frame, why not is velodyne frame?
Thanks in advance!