首页 > 论文 > 激光与光电子学进展 > 55卷 > 3期(pp:31008--1)

基于Kinect的实时手势识别

Real-Time Gesture Recognition Based on Kinect

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为实现基于Kinect传感器的实时手势识别, 并在保证识别精度的情况下缩短识别时间, 提出一种基于卡尔曼滤波的手势图像提取方法, 并研究基于该分割方法的三种特征的手势识别模型。通过Kinect获取图像和骨骼信息, 基于卡尔曼滤波提取手势区域。为验证分割的高效性, 采集10类手势的28000张样本, 提取两种局部二值模式特征和一种方向梯度直方图(HOG)特征, 用支持向量机(SVM)机器学习方法进行分类识别。实验表明, HOG+SVM的手势识别模型的识别精度可达97.09%, 识别帧率为31 frame/s。在基于Kinect的应用中, 基于该分割方法和HOG特征提取的SVM识别模型能够满足实时性的要求。

Abstract

In order to realize real-time gesture recognition based on Kinect and to reduce the recognition time while ensuring the recognition accuracy, we propose a method of gesture image extraction based on Kalman filter, and study a gesture recognition model based on three characteristics. We get depth images and skeleton information via Kinect, and then extract hand regions based on Kalman filter. In order to verify the efficiency of gesture segmentation, we collect 28000 samples of 10 types of gestures, extract two local binary pattern features and histogram of oriented gradient (HOG) feature, and classify the samples by support vector machine (SVM). The experimental results show that the gesture recognition model based on HOG+SVM has the recognition accuracy of 97.09% and the recognition rate of 31 frame/s. In application based on Kinect, HOG+SVM recognition model based on the proposed segmentation method can meet the real-time requirement.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP18

DOI:10.3788/lop55.031008

所属栏目:图像处理

基金项目:国家自然科学基金(61471260, 61205075)

收稿日期:2017-09-05

修改稿日期:2017-10-09

网络出版日期:--

作者单位    点击查看

鲍志强:天津大学电气自动化与信息工程学院, 天津 300072
吕辰刚:天津大学电气自动化与信息工程学院, 天津 300072

联系人作者:鲍志强(bzq1028@tju.edu.cn)

备注:鲍志强(1992-), 男, 硕士研究生, 主要从事图像处理方面的研究。E-mail: bzq1028@tju.edu.cn

【1】Huang D Y, Hu W C, Chang S H. Gabor filter-based hand-pose angle estimation for hand gesture recognition under varying illumination[J]. Expert Systems with Applications, 2011, 38(5): 6031-6042.

【2】Luo Y, Li L, Zhang B S, et al. Video hand tracking algorithm based on hybrid Cam Shift and Kalman filter[J]. Application Research of Computers, 2009, 26(3): 1163-1165.
罗元, 李玲, 张百胜, 等. 基于Cam Shift和Kalman滤波混合的视频手势跟踪算法[J]. 计算机应用研究, 2009, 26(3): 1163-1165.

【3】Tu S Q, Xue Y J, Liang Y, et al. Review on RGB-D image classification[J]. Laser & Optoelectronics Progress, 2016, 53(6): 060003.
涂淑琴, 薛月菊, 梁云, 等. RGB-D图像分类方法研究综述[J]. 激光与光电子学进展, 2016, 53(6): 060003.

【4】Lahamy H, Lichti D D. Towards real-time and rotation-invariant American Sign Language alphabet recognition using a range camera[J]. Sensors, 2012, 12(11): 14416-14441.

【5】Lun R, Zhao W. A survey of applications and human motion recognition with microsoft kinect[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2015, 29(5): 1555008.

【6】Raheja J L, Mishra A, Chaudhary A. Indian sign language recognition using SVM[J]. Pattern Recognition and Image Analysis, 2016, 26(2): 434-441.

【7】Kane L, Khanna P. Real-time recognition of medial structures within hand postures througheigen-space and geometric skeletal shape features[J]. Multimedia Tools and Applications, 2017, 76(3): 4571-4598.

【8】Ren Z, Yuan J, Meng J, et al. Robust part-based hand gesture recognition using kinect sensor[J]. IEEE Transactions on Multimedia, 2013, 15(5): 1110-1120.

【9】Shan C, Gong S, Mc Owan P W. Facial expression recognition based on local binary patterns: a comprehensive study[J]. Image and Vision Computing, 2009, 27(6): 803-816.

【10】Subrahmanyam M, Maheshwari R P, Balasubramanian R. Local maximum edge binary patterns: a new descriptor for image retrieval and object tracking[J]. Signal Processing, 2012, 92(6): 1467-1479.

【11】Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]. Computer Vision and Pattern Recognition, 2005: 886-893.

【12】Li S S, Zhao G P, Wang J Y. Distractor-aware object tracking based on multi-feature fusion and scale-adaption[J]. Acta Optica Sinica, 2017, 37(5): 0515005.
李双双, 赵高鹏, 王建宇. 基于特征融合和尺度自适应的干扰感知目标跟踪[J]. 光学学报, 2017, 37(5): 0515005.

【13】Pang Y, Yuan Y, Li X, et al. Efficient HOG human detection[J]. Signal Processing, 2011, 91(4): 773-781.

【14】Ojala T, Pietikinen M, Menp T. Gray scale and rotation invariant texture classification with local binary patterns[C]//European Conference on Computer Vision, 2000: 404-420.

【15】Pietikinen M, Ojala T, Xu Z. Rotation-invariant texture classification using feature distributions[J]. Pattern Recognition, 2000, 33(1): 43-52.

【16】Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.

【17】Yang Y, Ye M S. Chinese sign language recognition based on Kinect[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2013, 25(6): 834-841.
杨勇, 叶梅树. 基于Kinect的中国手语识别[J]. 重庆邮电大学学报(自然科学版), 2013, 25(6): 834-841.

【18】Liu B, Zhao X, Hu C H, et al. Gesture recognition method of hand over face occlusion in color and depth images[J]. Laser & Optoelectronics Progress, 2016, 53(6): 061001.
刘斌, 赵兴, 胡春海, 等. 面向颜色深度图像手脸近距遮挡的手势识别[J]. 激光与光电子学进展, 2016, 53(6): 061001.

【19】Yang B X, Hu X H, Huang J. Fingertip location through the gesture space points sets constructed by Kinect hand tracking[J]. Journal of Beijing Normal University (Natural Science), 2015, 51(6): 571-575.
杨博雄, 胡旭华, 黄静. 利用Kinect手部跟踪构造手势空间点集进行指尖定位的研究与实现[J]. 北京师范大学学报(自然科学版), 2015, 51(6): 571-575.

引用该论文

Bao Zhiqiang,Lü Chengang. Real-Time Gesture Recognition Based on Kinect[J]. Laser & Optoelectronics Progress, 2018, 55(3): 031008

鲍志强,吕辰刚. 基于Kinect的实时手势识别[J]. 激光与光电子学进展, 2018, 55(3): 031008

被引情况

【1】王民,郝静,要趁红,史其琦. 基于优化全卷积神经网络的手语语义识别. 激光与光电子学进展, 2018, 55(11): 111010--1

【2】王国庆,桂进斌,姜智翔,金晓宇. 交互式全息显示进展. 激光与光电子学进展, 2019, 56(8): 80004--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF