2025/09/29 by Bagladi, Milán Zsolt, Gulyás, László, Szalay, Gergő
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.2509.25042
This paper presents a real-time pipeline for dynamic arm gesture recognition based on OpenPose keypoint estimation, keypoint normalization, and a recurrent neural network classifier. The 1 x 1 normalization scheme and two feature representations (coordinate- and angle-based) are presented for the pipeline. In addition, an efficient method to improve robustness against camera angle variations is also introduced by using artificially rotated training data. Experiments on a custom traffic-control gesture dataset demonstrate high accuracy across varying viewing angles and speeds. Finally, an approach to calculate the speed of the arm signal (if necessary) is also presented.