The NN files are also provided inside the zip files - nn_model_path: minimum_image_publisher/models/yolov6n_openvino_2022.1_6shave.blob - nn_config_path: minimum_image_publisher/config/yolov6n.yaml
Description of the nodes
There are 3 nodes for comparison - image_publisher_node: pure color camera nodes and detection nodes for CAM_B and CAM_C, no ROS. - image_publisher_ros_node: pure color camera nodes and detection nodes for CAM_B and CAM_C, also ROS bridges to publish image and detection to ROS. - image_publisher_ros_single_detection_node: color camera nodes for both cameras, only one camera has detection node.
Severity of the issue for each node
For image_publisher_node, the blocking issue can be seen directly from the screen, it happens around 1 out of 10
image_publisher_node
166 KB
View full-sizeDownload For image_publisher_ros_node, we need pipeline_graph to see the FPS. It happens around 2 out of 5
image_publisher_ros_node
75.4 KB
View full-sizeDownload For image_publisher_ros_single_detection_node, we need pipeline_graph to see the FPS, I have NOT see the blocking happen yet
Build the latest docker image provided by depthai-ros in noetic branch.
Inside the container, create a catkin workspace and place the package under `<workspace>/src/`.
Update line 198 and 199 of `image_publisher.cpp` and other 2 version of image publisher source code to the actual NN file paths in your environment.
Run `catkin build` in the root of `<workspace>`.
Once the package is built. The application can be run by `rosrun minimum_image_publisher image_publisher_node` (make sure run `roscore` in another terminal, use `docker exec -it <container-ID> bash` to open another terminal from the container)
Or you can run the executable directly under `<workspace>/devel/lib/minimum_image_publisher/`