computer vision
Budget: $10 – $30 USD
I need python code to answer these questions :
1- Plot the image gradient vectors on top of the original image every N pixels (e.g. using short red lines segments of length K) and display the resulting image. Use a track bar to control N.
2- Scan the image with a window. At each window location, compute the correlation matrix and its eigenvalues. Multiply the eigenvalues you computed to get a 'cornerness" measure. Display the 'cornerness” measure making sure to normalize values as needed so that the measure is visible.
3- Detect and display corners in an image using the OpenCV Harris corner detection function (cornerHarris). Show the results using red dots. Use a track bar to control the number of control points shown.
Note: "Use a track bar to control the number of control points shown". So, you need to implement non-maximum suppression to remove the non-local maximum corners. Better corner localization is not required in this question.
1- Plot the image gradient vectors on top of the original image every N pixels (e.g. using short red lines segments of length K) and display the resulting image. Use a track bar to control N.
2- Scan the image with a window. At each window location, compute the correlation matrix and its eigenvalues. Multiply the eigenvalues you computed to get a 'cornerness" measure. Display the 'cornerness” measure making sure to normalize values as needed so that the measure is visible.
3- Detect and display corners in an image using the OpenCV Harris corner detection function (cornerHarris). Show the results using red dots. Use a track bar to control the number of control points shown.
Note: "Use a track bar to control the number of control points shown". So, you need to implement non-maximum suppression to remove the non-local maximum corners. Better corner localization is not required in this question.