Luc Van Gool, Professor for Computer Vision at the ETH in Zurich and the Katholieke Universiteit Leuven in Belgium talks about multi-tasking networks in autonomous vehicles Level 4+.
Luc leads research and teaches at both places. He has authored over 200 papers in his field. His main interests include 3D reconstruction and modeling, object recognition, and tracking and gesture analysis. He received several Best Paper awards (e.g. David Marr Prize ’98, Best Paper CVPR’07, Tsuji Outstanding Paper Award ACCV’09, Best Vision Paper ICRA’09). Furthermore, he is a co-founder of 5 spin-off companies.
In his case study, he tackles the question of how you can create leaner, faster and better networks in autonomous vehicles, so that their overall performance increases significantly. Luc also describes how audio functions are a way for passengers to influence the ride and the very importance of that tool in regards to the acceptance of self-driving cars.
Case study highlights:
- How to combine different tasks into a multi-tasking network
- Key points that need consideration when designing these networks
- Real-world application examples for mapping, recognition, and audio
Enjoy the video!