Lab course machine learning in signal processing

Imagine a car driving on an autobahn in an automatic mode. Among other things, the car needs to steer itself to keep driving in it's own lane. To accomplish this, the central problem is to detect the road-lane markings. These are the white solid or dashed lines that are drawn on each side of the lane. The standard modern approach to solve this type of problems is to take a large dataset of labeled examples and train a deep neural network model to accomplish the task. This is how car and pedestrian detection algorithms are developed. The difficulty with the road-lane markings is that there is no labeled dataset of them and creating such dataset would cost millions of dollars. In this lab course we will solve this problem using a dataset of simulated images intermixed with a dataset of real images that contain no road.

Time permitting, you will enhance the results by designing a network that analyses short video fragments.

The software will be developed in Python using Jupyter Notebook development kit. For deep learning you will use the PyTorch framework.

This is an advanced course, the knowledge of Python is assumed.

Database info is here.

Registration is here.

Time

  • Wednesday, 14:00 - 18:30, via Zoom

Assignments

Useful links