Real-time adaptive human motions for web-based training

Abstract

Web-based training offers many benefits over instructor-led training environments. It provides a time, class size and geographical location independent learning platform to students. To enable active learning and enhance the effectiveness in students' understanding of the training materials, multimedia cues, like 3D graphics, animation and sound, have been employed in web-based training systems to achieve these goals. However, if a training system involves a large amount of 3D animation, such as crowd animation in an emergency evacuation training system, the requirements for rendering capability and network bandwidth may become too high to meet. In this paper, we propose an adaptive human motion animation method to support real-time rendering and transmission of human motions in web-based training systems. Our method offers a mechanism to extract human motion data at various levels of detail (LoD). We also propose a set of importance factors to allow a web-based training system to determine the LoD of the human motion for rendering as well as the LoD for transmission, according to the importance of the motion and the available network bandwidth, respectively. We demonstrate the effectiveness of the new method with some experimental results. © Springer-Verlag Berlin Heidelberg 2005.