A Spatio-Temporal Multilayer Perceptron for Gesture Recognition

TL;DR

This paper introduces a novel spatio-temporal multilayer perceptron that effectively recognizes gestures from 3D body skeleton data, achieving state-of-the-art results for autonomous vehicle interaction.

Contribution

It presents a new neural network architecture that processes only skeleton data with spatial-temporal features and re-weighting, outperforming multimodal methods.

Findings

State-of-the-art accuracy on TCG and Drive&Act datasets.

Real-time gesture recognition on an autonomous vehicle.

Stable and efficient deployment in autonomous systems.

Abstract

Gesture recognition is essential for the interaction of autonomous vehicles with humans. While the current approaches focus on combining several modalities like image features, keypoints and bone vectors, we present neural network architecture that delivers state-of-the-art results only with body skeleton input data. We propose the spatio-temporal multilayer perceptron for gesture recognition in the context of autonomous vehicles. Given 3D body poses over time, we define temporal and spatial mixing operations to extract features in both domains. Additionally, the importance of each time step is re-weighted with Squeeze-and-Excitation layers. An extensive evaluation of the TCG and Drive&Act datasets is provided to showcase the promising performance of our approach. Furthermore, we deploy our model to our autonomous vehicle to show its real-time capability and stable execution.