Quantifying Sensor Simulation Quality - How Good is Good Enough?
Instructor: Alexander Braun, University of Applied Sciences Düsseldorf
Level: Intermediate
Duration: 4 hours
Course Date/Time: Sunday 15 January 13:30 - 17:45
Prerequisites: Basic technical understanding of sensor modalities for autonomous vehicles, especially camera systems.

Benefits:
This course enables the attendee to:

• Understand why and when it's important to quantify simulation quality.
• Role of realistic sensor simulations within different simulation environments.
• Get to know novel processes to quantify simulation quality.
• Understand how simulation and image quality relates to the performance of downstream ML/AI evaluation algorithms.

Course Description:
A relevant part of modern ADAS/AD development takes place in virtual simulation environments, and the simulations continuously become more and more realistic. But how realistic? How can you quantify the sensor accuracy for a given simulation, and how well do the simulations correlate with their real-world counterparts? How realistic do the sensors need to be simulated in the first place? This short course tackles these questions, providing both principle reasons why and where this topic is relevant, as well as concrete take-home proposals to quantify simulation quality.

Intended Audience:
Developers of simulation environments; users of simulation environments; with a focus on automotive, but transferable to other domains.

Alexander Braun received his diploma in physics with a focus on laser fluorescence spectroscopy from the University of Göttingen (2001). His PhD research in quantum optics and quantum computers was carried out at the University of Hamburg, resulting in a doctorate from the University of Siegen (2007). He started working as an optical designer for camera-based ADAS with the company Kostal, and later became responsible for the optical quality of the series mass production. Next, he became a professor of physics at the University of Applied Sciences Düsseldorf in 2013, where he now researches optical metrology and optical models for simulation in the context of autonomous driving. He is a member of DPG, SPIE, IS&T and VDI, participating in norming efforts at IEEE (P2020) and VDI (FA 8.13), and currently serves on the advisory board for the AutoSens conference, the IS&T Electronic Imaging Symposium, and for the VDI Optical Technologies (Fachbeirat 8).

Discounts given for multiple classes. See Registration Page for details to register.

For office use only: