camera calibration

[ssw2002com]

I have a question about the camera parameter. Do we need the chessboard to estimate the intrinsic mat and extrinsic mat?
Add following code to .datasets/CampusSeq1/Calibration/producePmat.m

K = cell(1,3);
K{1} = K1; K{2} = K2; K{3} = K3;
m_RT = cell(1,3);
m_RT{1} = RT1; m_RT{2} = RT2; m_RT{3} = RT3;
save('intrinsic.mat','K');
save('m_RT.mat', 'm_RT');
save('P.mat', 'P');
save('prjectionMat','P');

generate the camera_parameter.pickle

python ./src/tools/mat2pickle.py /parameter/dir ./datasets/CampusSeq1

[siehlema]

This depends on your calibration method. Many of them use a chessboard to perform intrinsic and extrinsic calibration.

After you performed the calibration the intrinsic: K and extrinsic: RT (combination of R and T) parameters should be accessible. You can then use the matlab script or use python+pickle to create the camera_parameter.pickle file, which is needed for a custom dataset.

[yuan0101213]

Hello, I just started learning cv.
When I ran "python ./src/tools/mat2pickle.py /parameter/dir ./datasets/CampusSeq1" to generate the camera_parameter.pickle , it told me "FileNotFoundError: [Errno 2] No such file or directory: '/parameter/dir/intrinsic.mat'" .
I wonder how the file (/parameter/dir/intrinsic.mat) generated?

[Taylorminer]

@yuan0101213 Do you solve the error? I meet the same bug.