Computer vision expert needed to remove distortion from video
Budget: $750 – $1,500 USD
The image distorted.png shows a single frame of a 90-minute video.
If one draws a line from the top left corner (see, distorted_left.png) to the right (see, distorted_right.png), the distortion is visible within the middle (see, distorted_middle.png)
The white line between the points to the left and the right should be straight but has a U-shape compared to the straight line in red.
Performing a camera calibration using open-cv (reference: https://docs.opencv.org/3.4.15/dc/dbb/tutorial_py_calibration.html) using 200 frames from two calibration videos each (see calibration_1_frame_0000000128.jpg, calibration_1_frame_0000000542.jpg, and calibration_1_frame_0000002578.jpg as examples for video 1 and calibration_2_frame_0000001512.jpg, calibration_2_frame_0000002152.jpg, and calibration_2_frame_0000002853.jpg for samples from video 2) results in what can be seen in undistorted.png.
Here, the line from the top left corner (see, undistorted_left.png) to the right (see, undistorted_right.png) overcorrected the distortion as the difference between the red-line and the white is an inverse U shape.
Your task is to fix the distortion correction by :
1) Looking through errors that I made within the python-script I wrote
2) Advise if the calibration videos need to be changed/adjusted
Note that I took the recording with an iPhone 11.
Use the word DISTORTION within your bid to be considered.
If one draws a line from the top left corner (see, distorted_left.png) to the right (see, distorted_right.png), the distortion is visible within the middle (see, distorted_middle.png)
The white line between the points to the left and the right should be straight but has a U-shape compared to the straight line in red.
Performing a camera calibration using open-cv (reference: https://docs.opencv.org/3.4.15/dc/dbb/tutorial_py_calibration.html) using 200 frames from two calibration videos each (see calibration_1_frame_0000000128.jpg, calibration_1_frame_0000000542.jpg, and calibration_1_frame_0000002578.jpg as examples for video 1 and calibration_2_frame_0000001512.jpg, calibration_2_frame_0000002152.jpg, and calibration_2_frame_0000002853.jpg for samples from video 2) results in what can be seen in undistorted.png.
Here, the line from the top left corner (see, undistorted_left.png) to the right (see, undistorted_right.png) overcorrected the distortion as the difference between the red-line and the white is an inverse U shape.
Your task is to fix the distortion correction by :
1) Looking through errors that I made within the python-script I wrote
2) Advise if the calibration videos need to be changed/adjusted
Note that I took the recording with an iPhone 11.
Use the word DISTORTION within your bid to be considered.