| 本文已被：浏览 3490次 下载 6180次 |
码上扫一扫！ |
|
|
| 连续交互空间下的混合手势交互模型 |
|
刘杰1,2,3, 黄进1, 田丰1, 胡伟平1, 戴国忠1, 王宏安1
|
|
1.人机交互北京市重点实验室(中国科学院 软件研究所), 北京 100190;2.中国科学院大学, 北京 100190;3.桂林电子科技大学 计算机与信息安全学院, 广西 桂林 541004
|
|
| 摘要: |
| 分析了触控交互技术在移动手持设备及可穿戴设备的应用现状及存在的问题.基于交互动作的时间连续性及空间连续性，提出了将触控交互动作的接触面轨迹与空间轨迹相结合，同时具有空中手势及触控手势的特性及优点的混合手势输入方法.基于连续交互空间的概念，将混合交互手势、空中手势、表面触控手势进行统一，建立了包括空中层、表面层、混合层的连续交互空间分层处理模型.给出了统一的信息数据定义及数转换流程.构建了通用性的手势识别框架，并对轨迹切分方法及手势分类识别方法进行了阐述.最后设计了应用实例，通过实验，对混合交互手势的可用性及连续空间分层处理模型的可行性进行了验证.实验结果表明，混合手势输入方式同时兼具了表面触控输入及空中手势输入的优点，在兼顾识别效率的同时，具有较好的空间自由度. |
| 关键词: 人机交互 手势交互 交互模型 交互空间 混合手势 |
| DOI：10.13328/j.cnki.jos.005123 |
| 分类号: |
| 基金项目:国家重点研发计划（2016YFB1001402）；国家自然科学基金（61422212，61232013，61170182，61273269）；国家高技术研究发展计划（863）（2015AA020506，2015AA016305） |
|
| Hybrid Gesture Interaction Model in the Continuous Interaction Space |
|
LIU Jie1,2,3, HUANG Jin1, TIAN Feng1, HU Wei-Ping1, DAI Guo-Zhong1, WANG Hong-An1
|
|
1.Beijing Key Laboratory of Human-Computer Interaction(Institute of Software, The Chinese Academy of Sciences), Beijing 100190, China;2.University of Chinese Academy of Sciences, Beijing 100190, China;3.School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, China
|
| Abstract: |
| This article analyzes the application and existing problems of touch interaction for mobile handsets and wearable device. Based on time continuity and space continuity of interactive action, a hybrid gesture input method with characteristic and advantages of air gesture and touch gestures is proposed by combining the contact trajectory and in-air trajectory of the interactive action. Based on the concept of continuous interaction space, hybrid interaction gestures, air gestures, and surface touch gestures are unified to establish a continuous interaction space hierarchical processing model including the air layer, surface layer and hybrid layer. The definition of information data and the transformation process are then provided. The general gesture recognition framework is also constructed. Furthermore, the trajectory segmentation method and gestures classification methods are introduced in detail. Finally, an application instance is designed, and the availability of the hybrid interaction gestures and feasibility of the continuous interaction space hierarchical processing model are verified. Experimental results show that the presented hybrid gesture interaction model possesses advantages of both air gesture and touch gestures, and has good recognition efficiency and better spatial freedom. |
| Key words: human-computer interaction gesture interaction interaction model interaction space hybrid gesture |
