基于多模态的雷达显控VR人机交互技术研究  

A Study on VR Human-computer Interaction Technology of Radar Display and Control Based on Multi-modal

作　　者：田胜[1] 赵立营 李维 TIAN Sheng;ZHAO Liying;LI Wei(Nanjing Research Institute of Electronics Technology,Nanjing 210039,China)

机构地区：[1]南京电子技术研究所,南京210039

出　　处：《现代雷达》2022年第7期56-60,共5页Modern Radar

摘　　要：针对目前虚拟现实(VR)人机交互技术在雷达领域应用较少,且主要集中在单模态交互上,导致VR显控体验感不佳的问题,文中基于视觉、听觉、手势等多模态开展雷达显控VR人机交互技术研究,提出了多模态VR交互系统架构、交互设计流程与方法、交互体验提升策略。在雷达VR显控中集成应用了人因手势、自然语音、智能眼控等多模态交互;同时基于多传感器设备,构建了多模态融合的VR自然交互体系,实现将手势、语音、眼控等行为数据融合,充分发挥多模态交互优势,有效增强雷达显控人机交互通道和效率,带来更加直观、自然、沉浸的用户体验。At present, VR human-computer interaction technology is seldom applied in radar field, and mainly focuses on single-modal interaction, resulting in poor experience of display and control. Based on multi-modal of vision, hearing and gesture, a study on VR interaction technology of radar display and control is carried out. VR multi-modal interaction system architecture, design process and methods, experience promotion strategies are proposed. And the human gesture, natural voice and intelligent eye control are innovatively integrated in radar VR multi-modal interaction. In addition, based on the multi-sensor equipment, VR multi-modal natural interaction system is built to realize the fusion of gesture, voice and eye control data. That gives full play to the advantages of multi-modal interaction to effectively enhance the interaction channel and efficiency, and bring more intuitive, natural and immersive user experience.

关 键 词：虚拟现实 多模态 人机交互 雷达显控 

分 类 号：TN957.7[电子电信—信号与信息处理]