stbt.match: Add structure_weighting #530
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
...into the heatmap.
We use Sobel edge detection to improve the matching. This is then taken into account when constructing the heatmap. This more closely matches human expectations at the cost of being slower to run. The weighting is done by raising the values to a power before multiplying them together. This is inspired by SSIM where seperate brightness, contrast and structure terms are combined with the same technique.
drothlis
reviewed
Feb 15, 2019
|
|
||
| images.append(cv2.Sobel(image, cv2.CV_32F, 0, 1, ksize=3)) | ||
| templates.append(cv2.Sobel(template, cv2.CV_32F, 0, 1, ksize=3)) | ||
| weights.append(structure_weighting * 0.5) |
There was a problem hiding this comment.
Why do the x & y Sobel separately?
There was a problem hiding this comment.
I see. Specifying xorder=1, yorder=1 gives diagonal edges, which isn't what we want.
|
Misc. thoughts:
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
We use Sobel edge detection to improve the matching. This is then
taken into account when constructing the heatmap. This more closely
matches human expectations at the cost of being slower to run.
The weighting is done by raising the values to a power before
multiplying them together. This is inspired by SSIM where seperate
brightness, contrast and structure terms are combined with the same
technique.
TODO: