Automatic Detection of 2D Human Postures Based on Single Images

Estimating human pose in static images is a challenging task due to the high dimensional state space, presence of image clutter and ambiguities of image observations. In this paper we propose a method to automatically detect human poses in a single image, based on a 2D model combined with anthropometric data. Furthermore, we use artificial neural networks to detect high level information about the human posture. Experimental results showed that the proposed technique performs well in non trivial images.