Implemented Robust Least Square for Rectangle Fitting on LIDAR Point Cloud#55
Merged
Conversation
ShisatoYano
reviewed
Feb 7, 2026
ShisatoYano
reviewed
Feb 7, 2026
ShisatoYano
requested changes
Feb 7, 2026
Owner
ShisatoYano
left a comment
ShisatoYano
left a comment
There was a problem hiding this comment.
I reviewed your implementation and it was almost great. Please just modify the header comment I left some comments. Thanks.
Contributor
Author
|
I made the change. |
ShisatoYano
approved these changes
Feb 8, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Results
RED: Robust LS, BLUE: Previous Geometric Approach
Description
This PR replaces the L-Shape rectangle fitting approach with an optimization-based rectangle detection pipeline for LIDAR point cloud.
Key Changes
Hybrid Initialization: Initializing the optimization with the geometric sweep approach for orientation and a diameter-based midpoint for spatial centering.
SDF Residual Function: Implemented a Signed Distance Field (SDF) calculation to determine point-to-box boundaries accurately in the local manifold.
M-Estimator Integration: Switched the optimizer loss to Huber, providing a significant improvement in RMSE by balancing surface noise averaging with outlier rejection.
Telemetry: Added a FittingDataTracker class to log and visualize performance metrics (RMSE and Localization accuracy) post-simulation.
Performance Impact
Stability: Eliminated orientation "flipping" and diagonal fitting.
Precision: Sub-degree heading accuracy and reduced center-point jitter.
Validation: RMSE comparison plots now clearly distinguish the refinement advantage over the raw geometric baseline.
How to Use