Weather Condition Estimation in Automated Vehicles

Weather Condition Estimation in Automated Vehicles

Wymenga, Jan (TU Delft Mechanical, Maritime and Materials Engineering)

Domhof, J.F.M. (mentor)
Gavrila, D. (graduation committee)
Kooij, J.F.P. (graduation committee)
Kober, J. (graduation committee)

Delft University of Technology

Mechanical Engineering | Biomechanical Design - BioRobotics

2018-05-15

This work presents a multi-sensor approach for weather condition estimation in automated vehicles. Using combined data from weather sensors (barometer, hygrometer, etc) and an in-vehicle camera, a machine learning and computer vision framework is employed to estimate the current weather condition in realtime and in-vehicle. The use of different sensor types is shown to improve robustness and reduce noise. The resulting modular framework allows it to be used with different sensor configurations, and allows changes in sensor configuration with minimal effort. Finally, a proof-of-concept experiment is presented; a dataset is recorded using a test vehicle and used for model evaluation.
The resulting datasets contains 20.000 pairs of video frames and sensor measurements recorded in different weather situations.

weather types
machine learning
intelligent vehicles
vision
driving
weather

http://resolver.tudelft.nl/uuid:421b3c6d-b85e-4876-a963-4094b35dea94

Student theses

master thesis

© 2018 Jan Wymenga