Package provides functionalities for using the Intel Realsense D435 camera combined with the yoloV8 object segmentation model implemented using ROS2.

pip install open3d
pip install ultralytics

Install colcon and rosdep, then build this repository:

mkdir -p ~/ros2_ws/src && cd ~/ros2_ws/src
git clone https://github.com/andreasHovaldt/yolov8_ros2.git
cd ~/ros2_ws
rosdep install --from-paths src --ignore-src -r -y
colcon build --symlink-install
source ~/ros2_ws/install/setup.bash

ros2 launch yolov8_ros2 camera_yolo.launch.py

This launches the camera node, and the yolov8 node. The image prediction results of the yolov8 segmentation are published to the topic: /yolo/prediction/image. These results are also published in a json formatted string to the topic: /yolo/prediction/item_dict.