feat(image_projection_based_fusion): add objects filter by rois

[yukke42]

Description

summary

• change passthrough_lower_bound_probability_threshold can be used for each class
• add this pakcage after centerpoint or pointpainting to filter false positives, especially for pedestrian.

including #4057

behavior

• bounding box on image
  • blue ... projected DetectedObjects from centerpoint
  • red ... RoIs from YOLOX
• bounding box on bev
  • blue ... output objects from this package
  • yellow ... false positives filtered out by this package

to show an image on screenshot, please change debug_mode=true on roi_detected_object_fusion.launch.xml

trust_distances

If the distance of obejct is greater than the threshold (50.0m for pedestrian), it's not discared by this package.

In the screenshot below, a pedestrian is filtered by this pacakge since YOLOX can not detect it even though pointpainting can detect it correctly. After adding trust distance, it cloud be output correctly from this package.

Related links

Tests performed

Notes for reviewers

Interface changes

Effects on system behavior

Pre-review checklist for the PR author

The PR author must check the checkboxes below when creating the PR.

• I've confirmed the contribution guidelines.
• The PR follows the pull request guidelines.

In-review checklist for the PR reviewers

The PR reviewers must check the checkboxes below before approval.

• The PR follows the pull request guidelines.
• The PR has been properly tested.
• The PR has been reviewed by the code owners.

Post-review checklist for the PR author

The PR author must check the checkboxes below before merging.

• There are no open discussions or they are tracked via tickets.
• The PR is ready for merge.

After all checkboxes are checked, anyone who has write access can merge the PR.

Summary by CodeRabbit

Release Notes:

• New Feature: Modified the signature of generateDetectedObjectRoIs and fuseObjectsOnImage functions to accept a DetectedObjects message instead of a vector of DetectedObject objects.
• New Feature: Added a new member variable can_assign_matrix of type Eigen::MatrixXi.
• New Feature: Modified member variables passthrough_object_flags_, fused_object_flags_, and ignored_object_flags_ to be maps with int64_t keys instead of vectors.
• New Feature: Added a new argument param_path with a default value to the launch file.
• New Feature: Included several new parameters for rois, camera info, and images in the launch file.
• New Feature: The roi_detected_object_fusion_node now reads parameters from the launch file.
• New Feature: Set the debug_mode parameter to true by default.
• Chore: Added a new dependency on object_recognition_utils in the package manifest file.

"With new signatures and maps so grand,
Parameters and dependencies expand.
Launch files read, debug mode set,
A fusion of features, no regrets."

[github-actions]

CodeRabbit

Walkthrough

The changes include modifications to the node.hpp file in the image_projection_based_fusion package, where the signature of two functions has been modified to accept a new message type. Additionally, new member variables have been added and existing ones have been modified to use maps instead of vectors. The launch/roi_detected_object_fusion.launch.xml file now includes new parameters and a default value for an argument. It also sets the debug_mode parameter to true by default. Finally, the package.xml file adds a new dependency on object_recognition_utils.

Changes

File	Summary
perception/image_projection_based_fusion/include/image_projection_based_fusion/roi_detected_object_fusion/node.hpp	- Added #include for a new message type. - Modified function signatures to accept a DetectedObjects message instead of a vector of DetectedObject objects. - Added a new member variable can_assign_matrix of type Eigen::MatrixXi. - Modified member variables to be maps with int64_t keys instead of vectors.
perception/image_projection_based_fusion/launch/roi_detected_object_fusion.launch.xml	- Added a new argument param_path with a default value. - Included several new parameters for rois, camera info, and images. - Modified the roi_detected_object_fusion_node to read these parameters from the launch file. - Set the debug_mode parameter to true by default.
perception/image_projection_based_fusion/package.xml	- Added a new dependency on object_recognition_utils.

[github-actions]

CodeRabbit

Commits

Files that changed from the base of the PR and between 9ad6493 and d2dffe6 commits.

Files selected (4)

• perception/image_projection_based_fusion/include/image_projection_based_fusion/roi_detected_object_fusion/node.hpp (3)
• perception/image_projection_based_fusion/launch/roi_detected_object_fusion.launch.xml (2)
• perception/image_projection_based_fusion/package.xml (1)
• perception/image_projection_based_fusion/src/roi_detected_object_fusion/node.cpp (10)

Files ignored due to filter (1)

• perception/image_projection_based_fusion/config/roi_detected_object_fusion.param.yaml

Files not summarized due to errors (1)

• perception/image_projection_based_fusion/src/roi_detected_object_fusion/node.cpp (diff tokens exceeds limit)

Files skipped from review due to trivial changes (1)

• perception/image_projection_based_fusion/package.xml

Review comments generated (10)

• Review: 9
• LGTM: 1

---

Tips

Chat with CodeRabbit Bot (@coderabbitai)

• Reply on review comments left by this bot to ask follow-up questions. A review comment is a comment on a diff or a file.
• Invite the bot into a review comment chain by tagging @coderabbitai in a reply.

Code suggestions

• The bot may make code suggestions, but please review them carefully before committing since the line number ranges may be misaligned.
• You can edit the comment made by the bot and manually tweak the suggestion if it is slightly off.

Pausing incremental reviews

• Add @coderabbitai: ignore anywhere in the PR description to pause further reviews from the bot.

[yukke42]

I want to merge PR ASAP, so it's opened now. But I need to tune params.
This PR conflicts with main branch because it depends on #4057.

[miursh]

LGTM

[codecov]

Codecov Report

Patch coverage has no change and project coverage change: -0.05% ⚠️

Comparison is base (7502305) 14.81% compared to head (4d68604) 14.76%.
Report is 7 commits behind head on main.

❗ Current head 4d68604 differs from pull request most recent head a5b84aa. Consider uploading reports for the commit a5b84aa to get more accurate results

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #4546      +/-   ##
==========================================
- Coverage   14.81%   14.76%   -0.05%     
==========================================
  Files        1527     1532       +5     
  Lines      105671   105973     +302     
  Branches    32100    32100              
==========================================
- Hits        15650    15649       -1     
- Misses      72943    73245     +302     
- Partials    17078    17079       +1     

Flag	Coverage Δ		*Carryforward flag
differential	0.00% <0.00%> (?)
total	14.81% <ø> (+<0.01%)	⬆️	Carriedforward from a4dec61

*This pull request uses carry forward flags. Click here to find out more.

Files Changed	Coverage Δ
...n_based_fusion/roi_detected_object_fusion/node.hpp	0.00% <ø> (ø)
...sed_fusion/src/roi_detected_object_fusion/node.cpp	0.00% <0.00%> (ø)

... and 8 files with indirect coverage changes

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[yukke42]

I have added thrust_distance and updated description.

[miursh]

LGTM

[yukkysaito]

LGTM