Jurewicz Katherina A, Neyens David M
Oklahoma State University, School of Industrial Engineering and Management, 329 Engineering North, College of Engineering, Architecture, and Technology, Stillwater, OK, 74078, USA.
Clemson University, Department of Industrial Engineering, 100 Freeman Hall, College of Engineering, Computing and Applied Sciences, Clemson, SC, 29634, USA.
Appl Ergon. 2022 Nov;105:103833. doi: 10.1016/j.apergo.2022.103833. Epub 2022 Jul 2.
3D gestural technology for HCI could transform the way people interact with computing systems. There are traditionally two approaches to developing gestural technology systems: a human-based approach where usability is maximized and a technology-based approach where system accuracy is maximized. The tradeoff between usability and accuracy may negatively affect the overall trust and reliability in the system. Therefore, this study seeks to redefine the human-based approach to gestural system development by introducing a bottom-up approach to identifying the lower-level features that produce a gesture, thus allowing the technology to accurately recognize features. A user elicitation study was performed, and gestures were classified according to a novel feature extraction gesture taxonomy and a traditional taxonomy of classifying gestures as a unit. The feature-extraction approach revealed several advantages because it fosters a bottom-up approach to identifying gesture features. Using this approach may mitigate the effects of the usability-accuracy tradeoff in gestural system development.
用于人机交互的3D手势技术可以改变人们与计算系统交互的方式。传统上，开发手势技术系统有两种方法：一种是以人类为基础的方法，即最大限度地提高可用性；另一种是以技术为基础的方法，即最大限度地提高系统准确性。可用性和准确性之间的权衡可能会对系统的整体信任度和可靠性产生负面影响。因此，本研究旨在通过引入一种自下而上的方法来识别产生手势的低级特征，从而重新定义基于人类的手势系统开发方法，使技术能够准确识别特征。进行了一项用户启发研究，并根据一种新颖的特征提取手势分类法和将手势作为一个单元进行分类的传统分类法对手势进行了分类。特征提取方法显示出几个优点，因为它促进了一种自下而上识别手势特征的方法。使用这种方法可能会减轻手势系统开发中可用性-准确性权衡的影响。
