Neural System recognizes Human Pointing Gestures in Real Images
Enno Littmann, Andrea Drees, Helge Joachim Ritter · 1996
. We present a neural network based system for the visual recognition of human hand pointing gestures from stereo pairs of video camera images. The accuracy of the current system allows to estimate the pointing target to an accuracy of 2 cm in a workspace area of 50x50 cm. The system consists of several neural networks arranged in a modular hierarchy. LLM networks perform the tasks of image segmentation, estimation of hand location, and estimation of 3D-pointing direction; a PSOM network yields the necessary coordinate transforms. Drawing heavily on the use of learning algorithms, the functions of all network modules were created from data examples only. 1 Introduction The development of advanced artificial neural systems challenges us with the task of finding architectures for the cooperation of multiple functional modules such that part of the structure of the overall system can be designed at a useful level of abstraction, but at the same time learning can be used to create or fine...