Myo手势识别方法在古建筑漫游系统中的应用

doi:10.16182/j.issn1004731x.joss.18-0847

摘要/Abstract

摘要： 博物馆展品众多,但展示方式单一,多用文字图片展现古建筑,无法给游客逼真体验,由此提出基于Myo臂环结合虚拟现实的古建筑漫游,以开封铁塔公园为例实现整体系统。设计得到游客佩戴Myo完成前进、转向、下蹲、停止动作时的加速度和陀螺仪值,设计SVM手势识别算法对特征值分类,设计对比实验验证算法的识别准确率和效率。建立特征值数据库,绘制其在固定时间内变化折线图,并用T-分布法求出置信区间。网格搜索和K-折验证法验证识别准确性,在动态环境中可达95%的准确率。系统实现对用户手势识别,提升用户与场景的交互性,可广泛应用到类似系统。

关键词: 古建筑模拟, 手势识别, 虚拟漫游, 人机交互, Myo

Abstract: Museum display many exhibits, but its display way is single. The ancient buildings are displayed by texts and pictures, so it cannot bring a realistic experience to the visitors. Therefore, the ancient architectural scene roaming based on Myo combined with virtual reality is proposed. Kaifeng Tower Park is used as an example to achieve the system. In the design, system gets visitors’ acceleration and gyroscope values of forward, turn, squat and stop by wearing Myo. SVM-based gesture recognition algorithm is designed to complete the classification of feature values. Contrast experiment is designed to verify accuracy and efficiency of algorithm. Database is established to draw a line graph of its change in a fixed time. T-distribution method is used to obtain the confidence interval. Grid search and K-fold verification method are used to test the gesture recognition. 95% accuracy can be achieved in a dynamic environment. The system realizes the recognition of user gestures and improves users’ interaction with the scene. It can be widely applied to similar systems.

Key words: ancient architecture simulation, gesture recognition, virtual roaming, human computer interaction, Myo

中图分类号:

TP391.9

薛艳萍, 王学松, 武仲科, 王醒策, 周明全. Myo手势识别方法在古建筑漫游系统中的应用[J]. 系统仿真学报, 2019, 31(9): 1907-1915.

Xue Yanping, Wang Xuesong, Wu Zhongke, Wang Xingce, Zhou Mingquan. Application of Myo Gesture Recognition Method in Ancient Building Roaming System[J]. Journal of System Simulation, 2019, 31(9): 1907-1915.

参考文献

[1] 程艳云, 边荟凇, 边长生. 基于图数据模型的聚类方法及可信度检测[J]. 系统仿真学报, 2018, 30(6): 2102-2116.
Cheng Yanyun, Bian Huizhen, Bian Changsheng.Clustering method and credibility detection based on graph data model[J]. Journal of System Simulation, 2018, 30(6): 2102-2116.
[2] 苗依迪, 吕军, 李秀梅. 两种基于压缩感知的图像数字水印方法[J]. 系统仿真学报, 2017, 29(11): 2649-2655.
Miao Yidi, Lü Jun, Li Xiumei.Two Image Digital Watermarking Methods Based on Compressed Sensing[J]. Journal of System Simulation, 2017, 29(11): 2649-2655.
[3] 龚正, 王强. 基于微观图像的图像拼接算法研究[J]. 计算机工程与应用, 2018, 54(2): 198-202.
Gong Zheng, Wang Qiang.Research on Image Mosaic Algorithm Based on Micro Image[J]. Computer Engineering and Applications, 2018, 54(2): 198-202.
[4] 张晓丽, 姚俊峰, 黄萍. 基于Kinect的实时360度虚拟试衣[J]. 系统仿真学报, 2016, 28(10): 2378-2384.
Zhang Xiaoli, Yao Junfeng, Huang Ping.Real-time 360-degree virtual fitting based on Kinect[J]. Journal of System Simulation, 2016, 28(10): 2378-2384.
[5] 李乾, 高尚兵, 潘志庚, 等. 基于无标记识别的增强现实方法研究[J]. 系统仿真学报, 2018, 30(7): 2608-2614.
Li Gan, Gao Shangbing, Pan Zhigeng, et al.Research on augmented reality method based on mark-free recognition[J]. Journal of System Simulation, 2018, 30(7): 2608-2614.
[6] 宋亮, 李志, 马兴瑞. 基于激光成像雷达的未知目标相对位姿估计算法[J]. 系统仿真学报, 2017, 29(5): 1103-1111.
Song Liang, Li Zhi, Ma Xingrui.Relative pose estimation algorithm for unknown targets based on laser imaging radar[J]. Journal of System Simulation, 2017, 29(5): 1103-1111.
[7] 张航, 陈彬, 薛含章, 等. 基于无人机和LIDAR的三维场景建模研究[J]. 系统仿真学报, 2017, 29(9): 1914-1920.
Zhang Hang, Chen Bin, Xue Hanzhang, et al.Research on 3D Scene Modeling Based on UAV and LIDAR[J]. Journal of System Simulation, 2017, 29(9): 1914-1920.
[8] Zaman F, Wong Y P, Yian Ng B.Density-based Denoising of Point Cloud[M]. Malaysia:9th International Conference on Robotic, Vision, Signal Processing and Power Applications. 2017: 287-295.
[9] 李泰国, 李文新, 王伟文, 等. 基于OpenGl空间机械臂三维重构可视化研究[J]. 计算机技术与发展, 2018, 1(1): 178-187.
Li Thaiguo, Li Wenxin, Wang Weiwen, et al.Visualization of 3D Reconstruction Based on OpenGl Space Manipulator[J]. Computer Technology and Development, 2018, 1(1): 178-187.
[10] Tredinnick R, Boettcher B, Smith S, et al.Uni-CAVE: A Unity3D plugin for non-head mounted VR display systems[C]. Virtual Reality. Los Angeles: IEEE, 2017: 393-394.
[11] Jun Z, Guanshan Z.The Development of Virtual Simulation Training System for Modern Greenhouse Based on Unity 3D[J]. China Modern Educational Equipment (S1673-1438), 2018, 14(3): 13-15.
[12] 程伯文, 郑一力, 黄青青, 等. 基于Unity3D的林木联合采育机虚拟训练系统研究[J]. 系统仿真学报, 2018, 30(4): 1310-1318.
Cheng Bowen, Zheng Yili, Huang Qingqing, et al.Virtual training system of forestry combined breeding machine based on Unity3D[J]. Journal of System Simulation, 2018, 30(4): 1310-1318.
[13] 王珊, 沈旭昆, 赵沁平. 三维人脸表情获取及重建技术综述[J]. 系统仿真学报, 2018, 30(7): 2423-2444.
Wang Shan, Shen Xukun, Zhao Qinping.A Survey of 3D Facial Expression Acquisition and Reconstruction Techniques[J]. Journal of System Simulation, 2018, 30(7): 2423-2444.
[14] Hasan M S, Yu H.Innovative developments in HCI and future trends[J]. International Journal of Automation & Computing (S1476-8186), 2017, 14(1): 1-11.
[15] 胡春花, 陈晓梅, 陈仕鸿. 虚拟现实技术在儿童室内火灾逃生教育中的应用研究[J]. 系统仿真学报, 2016, 28(4): 934-939.
Hu Chunhua, Chen Xiaomei, Chen Shihong.Application of Virtual Reality Technology in Children's Indoor Fire Escape Education[J]. Journal of System Simulation, 2016, 28(4): 934-939.
[16] 顾君忠. VR、AR和MR-挑战与机遇[J]. 计算机应用与软件, 2018, 35(3): 1-7.
Gu Junzhong.VR, AR and MR-challenge and Opportunity[J]. Computer Applications and Software, 2018, 35(3): 1-7.
[17] Houyi Y, Manlu L, Hua Z.Kinect depth map retrieval based on guided-sampling[J]. Application Research of Computers (S1001-3695), 2018, 14(8): 298-300.
[18] Ge L, Liang H, Yuan J, et al.3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation from Single Depth Images[C]. IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE Computer Society, 2017: 5679-5688.
[19] Liu H, Ju Z, Xiaofei Ji, et al.A Novel Approach to Extract Hand Gesture Feature in Depth Images[M]. Human Motion Sensing and Recognition. UK: Human Motion Sensing and Recognition, 2017: 193-205.
[20] 韩亮, 公璇, 王江云, 等. 跳伞模拟器人机交互可视化功能研究[J]. 系统仿真学报, 2017, 29(8): 1747-1752.
Han Liang, Gong Xuan, Wang Jiangyun, et al.Research on Human-Computer Interaction Visualization Function of Skydiving Simulator[J]. Journal of System Simulation, 2017, 29(8): 1747-1752.
[21] 赵新灿, 潘世豪, 王雅萍, 等. 沉浸式三维视线追踪算法研究[J]. 系统仿真学报, 2018, 30(6): 2027-2035.
Zhao Xincan, Pan Shihao, Wang Yaping, et al.Research on immersive 3D gaze tracking algorithm[J]. Journal of System Simulation, 2018, 30(6): 2027-2035.
[22] Lidan C, Zhe Z, Fengyi L, et al.Design of virtual training system for drop-out fuse operation based on VR devices[J]. Experimental Technology & Management (S1002-4965), 2017, 13(9): 119-122.
[23] Yang M J, Li J, Li H O, et al.VR English Education Game Development Based on Unity3D Platform[J]. Computer Knowledge & Technology, 2018, 5(17): 250-255.
[24] 张杰, 吴剑章, 汤嘉立, 等. 基于时空图像分割和交互区域检测的人体动作识别方法[J]. 计算机应用研究, 2017, 34(1): 302-305.
Zhang Jie, Wu Jianzhang, Tang Jiali, et al.Human motion recognition based on space-time image segmentation and interactive region detection[J]. Journal of Computer Applications, 2017, 34(1): 302-305.