Add exhaustive calibration fallback#286
Open
csherry04 wants to merge 1 commit into
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Added
cv2.CALIB_CB_EXHAUSTIVEto the SB fallback pathUpon testing was finding that it was not significantly slower and in many cases was faster due to less upsampled retries.
Compiled and tested lots of videos with the following results:
ACL are field videos where primary detector struggled, new fallback was better but still missing some, exhaustive was perfect
Comprehensive is my own set of calibrations with partial boards, distracting checkerboard-esque items to try and slow down exhaustive, etc
Utah set was passing with primary detector on my machine but not on others
Worth noting everything that failed with exhaustive was intended to fail.
Even in cases with no board, partial board, and distracting items, the exhaustive change was on average less than .1 seconds slower per video.
Included in PR is a new calibration testing file that runs through many of these trials and asserts correct behavior as well as low reprojection errors as well as a new more simple test in the main E2E testing file. Updated submodule to contain relevant videos