I am new to image processing and I need to use the KITTI 2015 stereo images for performing a depth estimation using Census transform and hamming distance. For this I to need to find out how to extract the baseline and focal length from the calibration files.
calib_cam_to_cam/000nr.txt file (nr = a number between 000 and 199 corresponding to the number of the pair of images in the dataset):
- S_xx: 1x2 size of image xx before rectification
- K_xx: 3x3 calibration matrix of camera xx before rectification
- D_xx: 1x5 distortion vector of camera xx before rectification
- R_xx: 3x3 rotation matrix of camera xx (extrinsic)
- T_xx: 3x1 translation vector of camera xx (extrinsic)
- S_rect_xx: 1x2 size of image xx after rectification
- R_rect_xx: 3x3 rectifying rotation to make image planes co-planar
- P_rect_xx: 3x4 projection matrix after rectification
calib_velo_to_cam/000nr.txt contains:
- R: the 3x3 rotation matrix that transforms a 3D point from the Velodyne coordinate system to the camera coordinate system.
- T: the 3x1 translation vector that transforms a 3D point from the Velodyne coordinate system to the camera coordinate system.
- delta_f: the difference between the focal lengths of the left and right color cameras, which is zero for monocular cameras.
- delta_c: the difference between the principal points of the left and right color cameras, which is zero for monocular cameras.
Thank you!
