Skip to content

This package enables the integration and operation of the OAK-D camera in ROS 2, allowing users to select different sensors and process image data. It provides configurable options for RGB, stereo, depth, disparity, and point cloud publishing, along with visualization in RViz, making it a versatile tool for computer vision applications

License

Notifications You must be signed in to change notification settings

jmguerreroh/oak_d_camera

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

OAK-D Camera ROS 2 Launcher

distro distro jazzy

This package provides a ROS 2 launch file to initialize and configure the OAK-D camera for RGBD, stereo, and point cloud processing. It includes adjustable camera configurations for transform frames, position, orientation, and depth processing parameters, along with a sample RViz configuration.

Installation

  1. Execute the below command to install the required dependencies:

    sudo wget -qO- https://docs.luxonis.com/install_dependencies.sh | bash

    Please refer to Installation documentation if any issues occur.

  2. Clone the repository and add it to your ROS 2 workspace:

    git clone https://github.com/jmguerreroh/oak_d_camera.git
  3. Install dependencies:

    rosdep install --from-paths src --ignore-src -r -y
  4. Build the workspace:

    colcon build --symlink-install

Usage

To launch the OAK-D camera node with default parameters:

ros2 launch oak_d_camera rgbd_stereo.launch.py

Launch Arguments

The launch file provides several configurable arguments:

Camera Parameters

  • camera_model: Model of the camera. Options: OAK-D, OAK-D-LITE. Default: OAK-D-LITE
  • tf_prefix: TF prefix for camera frames. Default: oak
  • base_frame: Name of the camera's base frame. Default: oak-d_frame
  • parent_frame: Parent frame for the camera's base. Default: oak-d-base-frame

Camera Position and Orientation

  • cam_pos_x, cam_pos_y, cam_pos_z: Camera position relative to the base frame. Default: 0.0
  • cam_roll, cam_pitch, cam_yaw: Camera orientation relative to the base frame. Default: 0.0

Depth Processing Parameters

  • lrcheck: Enable left-right consistency check. Default: True
  • extended: Enable extended disparity range. Default: False
  • subpixel: Enable subpixel accuracy. Default: True
  • confidence: Set confidence threshold for depth estimation. Default: 200
  • LRchecktresh: Set left-right consistency threshold. Default: 5

Please refer to StereoDepth documentation for more information.

Options

  • only_rgb: Enable publishing of only RGB images. Default: False
  • use_rviz: Launch RViz for visualization. Default: True use_depth: Enable depth image publishing. Default: True
  • use_disparity: Enable disparity image publishing. Default: True
  • use_lr_raw: Enable left and right raw image publishing. Default: True
  • use_pointcloud: Enable point cloud publishing. Default: True
  • pc_color: Use color in the point cloud. Options: True for color or False for intensity. Default: True

Visualizing in RViz

The launch file opens RViz with a pre-configured view. You can modify rviz/rgbd_stereo_pcl.rviz to customize the visualization.

About

This project was made by José Miguel Guerrero, Associate Professor at Universidad Rey Juan Carlos.

Copyright © 2024.

Twitter

License

This work is licensed under the terms of the MIT license.

License: MIT

About

This package enables the integration and operation of the OAK-D camera in ROS 2, allowing users to select different sensors and process image data. It provides configurable options for RGB, stereo, depth, disparity, and point cloud publishing, along with visualization in RViz, making it a versatile tool for computer vision applications

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published