Assignment: IMU data 1

Let There be IMU data 1

Deep Learning requires tremendous amounts of data, while acquiring real-world data is tedious. A state-of-the-art approach is to augment data that aids in training AI. This project investigates the opportunity to generate improved data using videos.

Task:

The goal is to extract IMU data from videos using Deep Learning. Real-world data comprising IMU data and videos from animals such as horses, goats, and sheep can be used to evaluate the approach.

Work:

20% Theory, 60% Simulations, 20%Writing

Contact:

Viet Duc Le, v.d.le@utwente.nl, room ZI