Feat/remove_noisy_segments #1885
Open
Conversation
This file contains hidden or 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
|
|
soumik12345
suggested changes
Jul 14, 2025
There was a problem hiding this comment.
Hi @AlexBodner, thanks for the PR!
I've added a few comments.
Can you also please resolve the pre-commit failures in the CI?
SkalskiP
requested changes
Jul 15, 2025
SkalskiP
requested changes
Jul 15, 2025
| @@ -1481,3 +1481,102 @@ def box_iou_batch_with_jaccard( | |||
| for d_idx, d in enumerate(boxes_detection): | |||
| ious[d_idx, g_idx] = _jaccard(d, g, is_crowd[g_idx]) | |||
| return ious | |||
|
|
|||
|
|
|||
| def remove_noisy_segments( | |||
There was a problem hiding this comment.
please add unit tests to remove_noisy_segments; make sure test are parametrized; you can take inspiration from test_mask_to_rle
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Outdated suggestions cannot be applied.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.
Description
This PR adds the function remove_noisy_segments to supervision/detection/utils.py. This function takes a mask and removes the connected components that are far away from the main component and that also are smaller than a threshold.
No dependencies added. It uses opencv.
Type of change
How has this change been tested, please provide a testcase or example of how you tested the change?
We provide unit test cases in the corresponding test_utils.py file.
Additionally, this function has been tested over some videos of the Basketball AI project, in which some masks had several components that were not connected and weren't desired. A con of this method is that it can remove desired objects, like occluded feet.
Some examples are:
Desired removals:
Undisired removals:
Before
boston-celtics-new-york-knicks-game-4-q1-05.06-05.01-3-second-rule_unfiltered.2.1.mp4
After:
boston-celtics-new-york-knicks-game-4-q1-05.06-05.01-3-second-rule_filtered.3.1.mp4
Mask comparison:
boston-celtics-new-york-knicks-game-4-q1-05.06-05.01-3-second-rule_compare.8.1.mp4
The difference is seen in the second 2 when the ball is passed and then when the ball is thrown
Docs
I only updated docs/detection/utils.md