OpenGV is a collection of computer vision methods for solving geometric vision problems. It is hosted and maintained by the Mobile Perception Lab of ShanghaiTech.
I have several cameras and dataset with flat (chessboard) pattern.
My goal is accurately estimate intrinsic, distortion and extrinsic of each camera to track objects in this cameras coordinate space using triangulation.
For each camera I perform single calibration to find intrinsic and distortion. After I make stereo calibration for all camera pair. But the result is unsatisfactory. I did all this with the OpenCV.
Can I use OpenGV
11. non-linear optimization over n correspondences (both central and non-central)
to improving the accuracy of previously found cameras parameters? (Global optimization all camera parameter together.)
I have several cameras and dataset with flat (chessboard) pattern. My goal is accurately estimate intrinsic, distortion and extrinsic of each camera to track objects in this cameras coordinate space using triangulation. For each camera I perform single calibration to find intrinsic and distortion. After I make stereo calibration for all camera pair. But the result is unsatisfactory. I did all this with the OpenCV. Can I use OpenGV
11. non-linear optimization over n correspondences (both central and non-central)
to improving the accuracy of previously found cameras parameters? (Global optimization all camera parameter together.)