Efficient Training & Testing of ADAS AI with synthetic data

This presention was made by Rodolphe TCHALEKIAN (ESI Group) at the GPU conference in Munich Germany under the Topic/Track: Deep Learning & AI: Autonomous vehicles.

Massive amounts of labeled and unlabeled datasets are needed both for training autonomous vehicles to navigate complex and unexpected driving scenarios, and to evaluate that training. As a substitute for hours of recorded data, Pro-SiVIC creates synthetic data to simulate the output from multiple sensor systems for outdoor scenarios that combine vehicles, obstacles, pedestrians, weather, and road conditions. We will demonstrate how powerful and efficient parallel computing with NVIDIA Drive PX2 can be used with Pro-SiVIC synthetic data to process that data in real time. We will compare the performance of a trained lane detection algorithm, running on Drive PX2, against a 3D Pro-SiVIC scene with simulated raw camera data, and a real video recorded from a car in similar conditions.