Create Path Detection Algorithm

[Jared-Chan]

Create a path detection algorithm in C++. Then integrate it into ROS2 by creating a triton_path_marker package and a path_detector node. The node should subscribe to the image topic of the down-facing camera and publish to a new topic the direction of the path marker.

It can be based on the triton_gate package and use functions form the triton_vision_utils package.

Another good reference here, it is in Python and it doesn't estimate the marker's direction, but it's a good place to start and to understand what steps are typically taken to detect objects.

Path marker details: RoboSub handbook (P.14)

Tasks

• Detect a path marker and its direction in simple images.

• Create a package triton_path_marker which will contain the component nodes needed to implement the algorithm. Don't worry about ROS2 at this stage, you could create an auto generated node when you create the triton_path_marker package and in the main function of the node you can write the algorithm and run it by using ros2 run.

• Integrate the algorithm into a series of one or more ROS2 components nodes and test how they work in the pipeline.