Refactor and enhance YOLO launch files and camera info publishing#46
Open
Refactor and enhance YOLO launch files and camera info publishing#46
Conversation
- Created a new launch file `camera_info.launch.py` to publish camera info from a YAML configuration. - Removed the old `perception.launch.py`, `pipeline_detection.launch.py`, `zed_composable_node.launch.py`, and `zed_yolo.launch.py` files to streamline the launch process. - Introduced `yolo_detect.launch.py` for the YOLOv8 TensorRT inference pipeline, including necessary configurations and nodes. - Added a new script `camera_info_publisher.py` to handle the publishing of camera information. - Updated `package.xml` to include new dependencies for the added functionality. - Created a placeholder for `yolo_obb.launch.py` for future development.
…nagement and clarity
jorgenfj
reviewed
Mar 18, 2026
Comment on lines
+17
to
+20
| # Input image dimensions | ||
| input_image_width: 1440 | ||
| input_image_height: 1080 | ||
| encoding_desired: "rgb8" |
Contributor
There was a problem hiding this comment.
Is this received input encoding or the encoding we convert to?
Contributor
Author
There was a problem hiding this comment.
its the encoding we receive
Contributor
There was a problem hiding this comment.
If it is the encoding we receive maybe rename it to input_encoding? encoding_desired makes it sound like it is something we are converting to
Contributor
|
Should make camera info publisher a cpp package to save 0.0001 secs during runtime, and because python... |
…iles and configurations
…input topics and dimensions
…nch files; update YOLO configurations and remove deprecated files
… files to reference camera settings
- Introduced a new visual inspection pipeline with a YAML configuration file for image filtering and ArUco detection. - Removed camera source definitions from YOLO configuration files to centralize camera settings in cameras.yaml. - Added new launch files for the FLIR Blackfly S BFS-PGE-16S2C-CS and RealSense D555 cameras. - Implemented image processing nodes for cropping and undistorting images with configurable parameters. - Enhanced pipeline launch files to dynamically resolve camera settings based on the enable_undistort flag. - Updated image_crop and image_undistort scripts to support passthrough functionality when undistortion is disabled. - Added a valve intervention pipeline that integrates YOLO OBB detection and valve landmark detection.
…d functionality and reliability
… in configuration and launch files
- Removed obsolete launch files: pipeline_localization.launch.py, valve_intervention.launch.py, visual_inspection.launch.py. - Updated YOLO launch files to streamline camera topic resolution from cameras.yaml. - Added a new script (tmux_perception.sh) to launch the perception stack in a tmux session for better monitoring and management. - Modified package.xml to remove unnecessary dependencies and added realsense2_camera and spinnaker_camera_driver.
- Introduced a new composable node `ImageUndistort` for undistorting images using camera calibration data. - Updated `CMakeLists.txt` to include necessary dependencies and build the new component. - Modified `cameras.yaml` to reflect changes in topic names and structure for the RealSense D555 camera. - Refactored launch files to integrate the new `ImageUndistort` component, replacing previous image processing nodes. - Enhanced `camera_info_publisher.py` to synchronize CameraInfo messages with image topics. - Added new launch files for visual inspection and valve intervention pipelines, utilizing the undistorted images. - Updated `package.xml` to include new dependencies for image processing and detection.
…nch and source files
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
4 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.
See vortexntnu/isaac_ros_image_segmentation#1 and vortexntnu/isaac_ros_object_detection#1