In this ROS LIVE-Class we’re going to learn how to create a ROS program that uses Tensorflow to recognize captured images from the robot camera, in real time. We are going to use a Gazebo drone simulation that flights over a space and recognizes the objects below it.
We will see:
▸ How to launch Tensorflow with a ROS program
▸ How to use a trained model to recognize objects
▸ How to feed the trained model from images obtained from the camera of the robot, in real time
▸ We will move the drone around and make it identify what its camera is seeing, in real time
Every Tuesday at 18:00 CET/CEST.
This is a LIVE Class on how to develop with ROS. In Live Classes you practice with me at the same time that I explain, with the provided free ROS material.
IMPORTANT: Remember to be on time for the class because at the beginning of the class we will share the code with the attendants.
IMPORTANT 2: in order to start practicing quickly, we are using the ROS Development Studio for doing the practice. You will need a free account to attend the class. Go to http://rds.theconstructsim.com and create an account prior to the class.
RELATED LINKS AND RESOURCES
- Tensorflow: https://www.tensorflow.org/
- ROS Deep Learning with TensorFlow 101
- Check all ROS LIVE-Classes