Minor correction on using tilted sensor model for OAK camera#1560
Merged
matlabbe merged 1 commit intointrolab:masterfrom Aug 5, 2025
Merged
Minor correction on using tilted sensor model for OAK camera#1560matlabbe merged 1 commit intointrolab:masterfrom
matlabbe merged 1 commit intointrolab:masterfrom
Conversation
matlabbe
reviewed
Aug 3, 2025
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
OAK cameras released after the end of 2024 use a tilted sensor model during factory calibration. That is, the two additional parameters tauX and tauY are enabled. So we now need to use intrinsic with 14 parameters instead of 8. This will slightly change the result of cv::getOptimalNewCameraMatrix() and theoretically also slightly improve SLAM accuracy.
https://docs.luxonis.com/hardware/platform/depth/calibration/#About%20Camera%20Calibration-Distortion%20Models
We found that the OAK camera also had other accuracy issues, and it always overestimated the distance to distant objects. The explanation their team gave me was that due to the nonlinear nature of disparity estimation, even if the cameras are perfectly calibrated and rectified, the depth estimation will be biased. This analysis is correct, but we find that the existing bias still exceeds the range given by this explanation. There may be other problems in its internal SGBM implementation, which we will study in the near future.