利用双目视觉视频的实时三维裸手手势识别

doi:10.3969/j.issn.1001-2400.2014.04.023

J4 ›› 2014, Vol. 41 ›› Issue (4): 130-136.doi: 10.3969/j.issn.1001-2400.2014.04.023

利用双目视觉视频的实时三维裸手手势识别

公衍超;万帅;杨楷芳;陈浩;李波

(西北工业大学电子信息学院，陕西西安 710072)

收稿日期:2013-09-03 出版日期:2014-08-20 发布日期:2014-09-25
通讯作者: 公衍超
作者简介:公衍超(1986-)，男，西北工业大学博士研究生，E-mail: ycgong@mail.nwpu.edu.cn．
基金资助:
国家自然科学基金资助项目(61371089)

Real-time 3D bare-hand gesture recognition using binocular vision videos

GONG Yanchao;WAN Shuai;YANG Kaifang;CHEN Hao;LI Bo

(School of Electronics and Information, Northwestern Polytechnical Univ., Xi'an 710072, China)

Received:2013-09-03 Online:2014-08-20 Published:2014-09-25
Contact: GONG Yanchao
About author:

摘要/Abstract

摘要：

为了解决三维裸手手势识别算法识别率低、易受类肤色物体干扰的问题，提出一种利用双目视觉视频的三维裸手手势识别算法．首先依据双目视觉原理推导出三维空间内手势深度与手势面积的关系，基于此关系对三维手势进行快速识别．为进一步降低算法复杂度，根据极线约束规则提出一种只计算手势质心匹配点的立体匹配算法．实验结果表明，与现有算法相比，所提算法性能在处理速度、识别准确率、鲁棒性方面均有明显提高．同时，提出的算法具有较强的开放性，可进一步根据需求定义、添加需识别的三维手势．

关键词: 手势识别, 双目视觉, 立体匹配, 极线约束

Abstract:

Current bare-hand based gesture recognition algorithms generally have the problems of low recognition accuracy and being prone to be affected by skin-like objects. In this paper, a 3D bare-hand gesture recognition algorithm is proposed using binocular vision videos. Firstly, a relationship between the depth and area of the gesture is achieved according to the principle of binocular vision, on the basis of which fast 3D gesture recognition is realized. To further speed up the method, a fast stereo matching algorithm is proposed following the epipolar line constraint rule, which regards the gesture's centroid as the matching point. Experimental results have demonstrated that compared with existing algorithms the proposed algorithm significantly improves the performance in processing speed, recognition accuracy, and robustness. It should be noted that the proposed algorithm is open, where more 3D gestures can be easily added upon requirement.

Key words: gesture recognition, binocular vision, stereo matching, epipolar line constraint

中图分类号:

TP391

公衍超;万帅;杨楷芳;陈浩;李波. 利用双目视觉视频的实时三维裸手手势识别[J]. J4, 2014, 41(4): 130-136.

GONG Yanchao;WAN Shuai;YANG Kaifang;CHEN Hao;LI Bo. Real-time 3D bare-hand gesture recognition using binocular vision videos[J]. J4, 2014, 41(4): 130-136.

参考文献

［1］马英红, 杨家玮, 惠雷放, 等. 一种新颖的手部运动跟踪系统［J］. 西安电子科技大学学报, 2012, 39 (1): 79-85.
Ma Yinghong, Yang Jiawei, Hui Leifang, et al. Novel Hand Motion Tracking System ［J］. Journal of Xidian University, 2012, 39 (1): 79-85.
［2］ Kumar P, Rautaray S S, Agrawal A. Hand Data Glove: a New Generation Real-time Mouse for Human-computer Interaction ［C］//Proceedings of IEEE International Conference on Recent Advances in Information Technology. Piscataway: IEEE, 2012: 750-755.
［3］ Han Y M. A Low-cost Visual Motion Data Glove as an Input Device to Interpret Human Hand Gestures ［J］. IEEE Transactions on Consumer Electronics, 2010, 56(2): 501-509.
［4］ Murthy G R S, Jadon R S. Hand Gesture Recognition Using Neural Network ［C］//Proceedings of 2010 IEEE 2nd International Advance Computing Conference. Piscataway: IEEE, 2010: 134-138.
［5］ Varkonyi K A R, Tusor B. Human-computer Interaction for Smart Environment Applications Using Fuzzy Hand Posture and Gesture Models ［J］. IEEE Transactions on Instrumentation and Measurement, 2011, 60(5): 1505-1514.
［6］ Yun L, Peng Z. An Automatic Hand Gesture Recognition System Based on Viola-jones Method and SVMs ［C］//Proceedings of International Workshop on Computer Science and Engineering. Piscataway: IEEE, 2009: 72-76.
［7］ Qing C, Georganas N D, Petriu E M. Real-time Vision-based Hand Gesture Recognition Using Haar-like Features ［C］//Proceedings of IEEE International Conference on Instrumentation and Measurement Technology. Piscataway: IEEE, 2007: 1-6.
［8］ Sohn M K, Lee S H, Kim D J, et al. 3D Hand Gesture Recognition from One Example ［C］//Proceedings of IEEE International Conference on Consumer Electronics. Piscataway: IEEE, 2013: 171-172.
［9］ Sato Y, Saito M, Koike H. Real-time Input of 3D Pose and Gestures of a User's Hand and Its Applications for HCI ［C］//Proceedings of Virtual Reality Annual International Sympoisium. Piscataway: IEEE, 2001: 79-86.
［10］向登宁, 邓文怡. 利用极线约束方法实现图像特征点的匹配［J］. 北京机械工业学院学报, 2002, 17(4): 21-25.
Xiang Dengning, Deng Wenyi. Image Feature Points Matching Using the Epipolar Line Constraint ［J］. Journal of Beijing Institute of Machinery, 2002, 17(4): 21-25.
［11］贾静, 吴成柯. 秩1约束下基于圆球的相机标定算法［J］. 西安电子科技大学学报, 2013, 40(2): 1-4.
Jia Jing, Wu Chengke. Rank-1 Constraint for Camera Calibration Based on Spheres ［J］. Journal of Xidian University, 2013, 40(2): 1-4.
［12］汪云飞, 毕笃彦, 黄飞. 一种用于图像分割的等周算法改进［J］. 西安电子科技大学学报, 2012, 39(2): 87-94.
Wang Yunfei, Bi Duyan, Huang Fei. Improved Isoperimetric Algorithm for Image Segmentation ［J］. Journal of Xidian University, 2012, 39(2): 87-94.
［13］ Zhang Z Y. Camera Calibration with One-dimensional Objects ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(7): 892-899.
［14］ Cai J, Goshtasby A. Detecting Human Faces in Color Images ［J］. Image and Vision Computing, 1999, 18(1): 63-75.
［15］陈忠碧, 张启衡. 一种适合于多目标检测的图像分割方法［J］. 光电工程, 2004, 31(5): 34-37.
Chen Zhongbi, Zhang Qiheng. An Image Segmentation Algorithm Suitable for Multi-object Detection ［J］. Opto-Electronic Engineering, 2004, 31(5): 34-37.
［16］刘焕云, 王军宁, 何迪, 等. 仿生模式识别目标自适应跟踪算法［J］. 西安电子科技大学学报, 2013, 40(4): 142-148.
Liu Huanyun, Wang Junning, He Di, et al. Research on Biomimetic Pattern Recognition for Object Adaptive Tracking Algorithm ［J］. Journal of Xidian University, 2013, 40(4): 142-148.
［17］ Bradski G, Kaehler A. Learning OpenCV: Computer Vision with the OpenCV Library ［M］. Sebastopol: O'Reilly Media Incorporated, 2008: 405-458.

[1]	郭大波1;2;卢朝阳1;何华君1;焦卫东1. 一种新的立体视差估计算法 [J]. J4, 2007, 34(3): 337-341.
[2]	何华君;卢朝阳;焦卫东;郭大波. 基于梯度和MRF模型的视差估计算法 [J]. J4, 2007, 34(3): 373-376.

利用双目视觉视频的实时三维裸手手势识别

Real-time 3D bare-hand gesture recognition using binocular vision videos

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

Metrics

本文评价

推荐阅读 10