Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles
This work addresses safety and interaction challenges for autonomous vehicles in real-world traffic, though it is incremental in combining existing modalities.
The paper tackles gesture recognition for autonomous vehicles by fusing camera and radar data, achieving improved performance and demonstrating robustness when one sensor fails.
We present a joint camera and radar approach to enable autonomous vehicles to understand and react to human gestures in everyday traffic. Initially, we process the radar data with a PointNet followed by a spatio-temporal multilayer perceptron (stMLP). Independently, the human body pose is extracted from the camera frame and processed with a separate stMLP network. We propose a fusion neural network for both modalities, including an auxiliary loss for each modality. In our experiments with a collected dataset, we show the advantages of gesture recognition with two modalities. Motivated by adverse weather conditions, we also demonstrate promising performance when one of the sensors lacks functionality.