基于加锁机制的静态手势识别方法

doi:10.11772/j.issn.1001-9081.2016.07.1959

计算机应用 ›› 2016, Vol. 36 ›› Issue (7): 1959-1964.DOI: 10.11772/j.issn.1001-9081.2016.07.1959

基于加锁机制的静态手势识别方法

王红霞¹, 王坤²

1. 武汉理工大学计算机科学与技术学院, 武汉 430063;
2. 武汉光电国家实验室(华中科技大学), 武汉 430074

收稿日期:2015-12-17 修回日期:2016-03-15 出版日期:2016-07-10 发布日期:2016-07-14
通讯作者: 王红霞
作者简介:王红霞(1977-),女,湖北洪湖人,副教授,博士,主要研究方向:图像处理、模式识别;王坤(1992-),男,湖北孝感人,硕士研究生,主要研究方向:多媒体数据挖掘。
基金资助:
湖北省自然科学基金资助项目（2013CFB351）；中央高校基本科研业务费专项资金资助项目（2014-IV-105）。

Static gesture recognition method based on locking mechanism

WANG Hongxia¹, WANG kun²

1. School of Computer Science and Technology, Wuhan University of Technology, Wuhan Hubei 430063, China;
2. Wuhan National Laboratory for Optoelectronics (Huazhong University of Science and Technology), Wuhan Hubei 430074, China

Received:2015-12-17 Revised:2016-03-15 Online:2016-07-10 Published:2016-07-14
Supported by:
This work is partially supported by the Natural Science Funds of Hubei Province (2013CFB351), the Fundamental Research Funds for the Central Universities (2014-IV-105).

摘要/Abstract

摘要： 基于RGB-D（RGB-Depth）的静态手势识别的速度高于其动态手势识别，但是存在冗余手势和重复手势而导致识别准确性不高的问题。针对该问题，提出了一种基于加锁机制的静态手势识别方法来识别运动中的手势。首先，将通过Kinect设备获取RGB数据流和Depth数据流融合成人体骨骼数据流；然后，在静态手势方法中引入加锁机制，并与之前建立好的骨骼点特征模型手势库进行比对计算；最后，设计一款“程序员进阶之路”益智类网页游戏进行应用与实验。实验验证在6种不同运动手势情况下，该方法与纯静态手势识别方法相比，平均识别准确率提高了14.4%；与动态手势识别相比，识别速度提高了14%。实验结果表明，提出的基于加锁机制的静态手势识别方法，既保留了静态识别的速率，实现了实时识别；又能很好地剔除冗余手势和重复手势，提高了识别正确性。

关键词: RGB-D, Kinect, 骨骼数据, 手势识别, 加锁机制

Abstract: The static gesture recognition speed is higher than that of dynamic gesture recognition for RGB-D (RGB-Depth) data, but redundancy gestures and repeated gestures lead to low recognition accuracy. In order to solve the problem, a static gesture recognition method based on locking mechanism was proposed. First, RGB data flow and the Depth data stream were obtained through Kinect equipment, then two kinds of data flow were integrated into human body skeleton data flow. Second, the locking mechanism was used to identify static gestures, and comparison and calculation were done with the established bone point feature model gesture library before. Finally, an "advanced programmers road" brain-training Web game was designed for application and experiment. In the experiments of six different movement gestures, compared with the static gesture recognition method, the average recognition accuracy of the proposed method was increased by 14.4%; compared with the dynamic gesture recognition method, the gesture recognition speed of the proposed method was improved by 14%. The experimental results show that the proposed method keeps the high speed of static recognition method, realizes the real-time recognition; and also improves the identification accuracy through eliminating redundant repeated gestures.

Key words: RGB-Depth (RGB-D), Kinect, skeleton data, gesture recognition, locking mechanism

中图分类号:

王红霞, 王坤. 基于加锁机制的静态手势识别方法[J]. 计算机应用, 2016, 36(7): 1959-1964.

WANG Hongxia, WANG kun. Static gesture recognition method based on locking mechanism[J]. Journal of Computer Applications, 2016, 36(7): 1959-1964.

参考文献

[1] CHOI W, PANTOFARU C, SAVARESE S. A general framework for tracking multiple people from a moving camera[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(7):1577-1591.
[2] REN Z, YUAN J, MENG J, et al. Robust hand gesture recognition based on finger-earth mover's distance with a commodity depth camera[C]//MM'11:Proceedings of the 19th ACM International Conference on Multimedia. New York:ACM, 2011:1093-1096.
[3] YANG C, JANG Y, BEHETC J. Gesture recognition using depth-based hand tracking for contactless controller application[C]//ICCE 2012:Proceedings of the 2012 IEEE International Conference on Consumer Electronics. Piscataway, NJ:IEEE, 2012:297-298.
[4] OSZUST M, WYSOCKI M. Polish sign language words recognition with Kinect[C]//HSI 2013:Proceedings of the 20136th International Conference on Human System Interactions. Washington, DC:IEEE Computer Society, 2013:219-226.
[5] CHAI X, LI G, LIN Y, et al. Sign language recognition and translation with Kinect[C]//FG 2013:Proceedings of the 10th IEEE International Conference on Automatic Face and Gesture Recognition. Washington, DC:IEEE Computer Society, 2013:22-26.
[6] CHAI X, LI G, CHEN X, et al. A tool to support communication between deaf and hearing persons with the Kinect[C]//ASSETS 2013:Proceedings of the 15th International ACM SIGACCESS Conference on Computers and Accessibility Proceedings. New York:ACM, 2013:21-23.
[7] 林海波,梅为林,张毅,等.基于Kinect骨骼信息的机械臂体感交互系统的设计与实现[J].计算机应用与软件,2013,30(2):157-160.(LIN H B, MEI W L, ZHANG Y, et al. Design and implementation of robot arm somatosensory interaction system based on Kinect skeletal information[J]. Computer Applications and Software, 2013, 30(2):157-160.)
[8] ZHAO Y, LIU Z, CHENG H. RGB-depth feature for 3D human activity recognition[J]. China Communication, 2013, 10(7):93-103.
[9] WANG Y, SHI Y. Human activities segmentation and location of key frames based on 3D skeleton[C]//CCC 2014:Proceedings of the 33rd Chinese Control Conference. Washington, DC:IEEE Computer Society, 2014:4786-4790.
[10] CHEN H, LIU T, GE M, et al. A depth optimization method for 2D-to-3D conversion based on RGB-D images[C]//IEEE IC-NIDC 2014:Proceedings of the 20144th IEEE International Conference on Network Infrastructure and Digital Content. Piscataway, NJ:IEEE, 2014:223-227.
[11] 郑立国,刘杨,罗江林,等.基于RGB-D数据的实时人体检测算法[J].吉林大学学报(信息科学版),2015,33(2):214-218.(ZHENG L G, LIU Y, LUO J L, et al. Implementation of real-time human body detection based on RGB-D data[J]. Journal of Jilin University (Information Science Edition), 2015, 33(2):214-218.)
[12] SHOTTON J, FITZGIBBON A, COOK M, et al. Real-time human pose recognition in parts from single depth images[C]//CVPR 2011:Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2011:1297-1304.

[1]	赵宏, 刘向东, 杨永娟. 基于RGB-D图像的室内机器人同时定位与地图构建[J]. 计算机应用, 2020, 40(12): 3637-3643.
[2]	喻露, 胡剑锋, 姚磊岳. 基于人体骨架的非标准深蹲姿势检测方法[J]. 计算机应用, 2019, 39(5): 1448-1452.
[3]	袁泉, 张建峰, 伍立志. 基于改进LBE特征的RGB-D显著性检测[J]. 计算机应用, 2018, 38(5): 1432-1435.
[4]	张全贵, 蔡丰, 李志强. 基于耦合多隐马尔可夫模型和深度图像数据的人体动作识别[J]. 计算机应用, 2018, 38(2): 454-457.
[5]	谢小雨, 刘喆颉. 基于肌电信号和加速度信号的动态手势识别方法[J]. 计算机应用, 2017, 37(9): 2700-2704.
[6]	侯荣波, 魏武, 黄婷, 邓超锋. 基于ORB-SLAM的室内机器人定位和三维稠密地图构建[J]. 计算机应用, 2017, 37(5): 1439-1444.
[7]	骆健, 蒋旻. 基于RGB-D图像核描述子的物体识别方法[J]. 计算机应用, 2017, 37(1): 255-261.
[8]	杜堃, 谭台哲. 复杂环境下通用的手势识别方法[J]. 计算机应用, 2016, 36(7): 1965-1970.
[9]	王梅, 于远芳, 屠大维, 周华. 基于Kinect的环境平面特征提取与重构[J]. 计算机应用, 2016, 36(5): 1366-1370.
[10]	蒋穗峰, 李艳春, 肖南峰. 基于手势识别的工业机器人操作控制方法[J]. 计算机应用, 2016, 36(12): 3486-3491.
[11]	陆中秋, 侯振杰, 陈宸, 梁久祯. 基于深度图像与骨骼数据的行为识别[J]. 计算机应用, 2016, 36(11): 2979-2984.
[12]	尚常军, 丁瑞. 基于曲率局部二值模式的深度图像手势特征提取[J]. 计算机应用, 2016, 36(10): 2885-2889.
[13]	谈家谱, 徐文胜. 基于Kinect的指尖检测与手势识别方法[J]. 计算机应用, 2015, 35(6): 1795-1800.
[14]	刘红, 刘蓉, 李书玲. 基于随机投影的加速度手势识别[J]. 计算机应用, 2015, 35(1): 189-193.
[15]	张毅刘钰然罗元. 基于视觉的手势识别方法及其在数字信号处理器上的实现[J]. 计算机应用, 2014, 34(3): 833-836.

基于加锁机制的静态手势识别方法

Static gesture recognition method based on locking mechanism

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics