Abstract
Recognition of hand gestures is one of the most fundamental tasks in human-robot interaction. Sparse representation based methods have been widely used due to their efficiency and low requirements on the training data. Recently, nonconvex regularization techniques including the $\ell_{1-2}$ regularization have been proposed in the image processing community to promote sparsity while achieving efficient performance. In this paper, we propose a vision-based human arm gesture recognition model based on the $\ell_{1-2}$ regularization, which is solved by the alternating direction method of multipliers (ADMM). Numerical experiments on realistic data sets have shown the effectiveness of this method in identifying arm gestures.
Abstract (translated)
URL
https://arxiv.org/abs/2104.14349