Augmenting Visual AI through Radar and Camera Fusion

In this presentation Sébastien Taylor discusses well-known limitations of camera-based AI and how radar can be leveraged to address these limitations. He will cover common radar data representations and how AI can be used on radar. He’ll then explain how radar and camera data can be fused into a single sensor-fusion AI model. He will also dive into low-level radar data cubes and how these can provide richer data for the model while introducing some new challenges, and he’ll discuss methods to tackle these challenges. Finally he will explore some example scenarios comparing a radar-camera combination with a stereo camera to highlight the trade-offs of the two approaches.