基于虚拟现实技术的智能游戏人机交互系统设计  

Design of Intelligent Game Human Computer Interaction System Based on Virtual Reality Technology

作　　者：罗银 LUO Yin(Sichuan Tianfu New Area Information Vocational College,Meishan Sichuan 620564,China)

机构地区：[1]四川天府新区信息职业学院,四川眉山620564

出　　处：《自动化与仪器仪表》2024年第10期287-291,共5页Automation & Instrumentation

摘　　要：针对现代基于虚拟现实技术(Virtual Reality,VR)的智能游戏的人机交互系统设计问题,研究引入了改进的强度场与关联字段(Part Intensity Fields-Part Association Fields,PIF-PAF)人体关键点检测算法进行人体的二维关键点检测,同时采用了人体关键点升维算法,并设计了基于VR技术的智能游戏的人机交互系统。结果显示,PIF-PAF算法的对象关键点相似性均高于其余两种算法,其平均值高达97.81%。改进PIF-PAF算法的归一化方差平均值仅为0.215%,相比于其余两种算法分别降低了0.041%、0.029%。此外,改进PIF-PAF算法的平均检测速度高达18.6 fps,相比于传统PIF-PAF算法增加了5.4 fps。说明研究所提人体关键点检测算法具有显著优势,且该人机交互系统具有良好的实际应用效果。这为现代智能VR游戏交互系统提供了高效、准确的人机交互基础。In response to the design problem of human-computer interaction system for modern intelligent games based on Virtual Reality(VR)technology,this study introduces an improved Part Intensity Fields Part Association Fields(PIF-PAF)human keypoint detection and calculation method for two-dimensional human keypoint detection.At the same time,the human keypoint dimensionality enhancement algorithm is adopted,And designed a human-computer interaction system for intelligent games based on VR technology.The results show that the object key point similarity of the PIF-PAF algorithm is higher than the other two algorithms,with an average value of 97.81%.The average normalized variance of the improved PIF-PAF algorithm is only 0.215%,which is 0.041%and 0.029%lower than the other two algorithms,respectively.In addition,the average detection speed of the improved PIF-PAF algorithm is as high as 18.6 fps,which is 5.4 fps more than the traditional PIF-PAF algorithm.The human key point detection algorithm proposed by the research institute has significant advantages,and the human-computer interaction system has good practical application effects.This provides an efficient and accurate human-machine interaction foundation for modern intelligent VR game interaction systems.

关 键 词：虚拟现实技术 智能游戏 人机交互 系统设计 PIF-PAF 

分 类 号：TP11[自动化与计算机技术—控制理论与控制工程]