Closed niannianmeng closed 6 years ago
"does it mean Rotation_KeyFrame *(x-Translation_KeyFrame)" It's R^T (x - t)
" image coordinates for the feature point of each frame by Rotation_frame.inverse()Xs-Translation_frame" It's R X + t which equals to R (X - p). The class CameraPose does not store translation but position p = -R^T * t. Please see comments in https://github.com/baidu/ICE-BA/blob/3e2bfe76f34edac61400f875aa2901f989a4c2c7/Backend/IBA/IBA_datatype.h#L62
Hi, haomin, thanks a lot for your explanation. I still have a doubt that R is represented in the camera coordinate system, right? Do we need to convert it to the imu coordinate system by m_Ru and m_Pu?
R is represented in the camera coordinate system. If you want IMU pose rather than camera pose, you have to do the conversion.
Ok, thanks for your reply.
The problem has been solved.
In the callback function, slidingwindow.Xs are obtained, I think the Xs represent the word 3D points. is it right? According to the GetSlidingWindow function , the Xs are obtained by C.ApplyInversely(x). does it mean Rotation_KeyFrame (x-Translation_KeyFrame)? but when i want to get image coordinates for the feature point of each frame by Rotation_frame.inverse()Xs-Translation_frame, I found the points drift when the image motion happen. anyone can help me for this question?