Hand real-time tracking method based on neural network and Kalman filter

Gong-ren ZENG; Jian-min YAO; Qun YAN; Zhi-xian LIN; Tai-liang GUO; Chang LIN

doi:10.3788/YJYXS20203505.0464

您当前的位置：

首页 >

文章列表页 >

Hand real-time tracking method based on neural network and Kalman filter

Image Processing | 更新时间：2020-08-12

- Hand real-time tracking method based on neural network and Kalman filter
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 5, Pages: 464-470(2020)
- 作者机构：
  
  1.平板显示技术国家地方联合工程实验室, 福州大学物理与信息工程学院, 福建福州 350108
  2.晋江市博感电子科技有限公司, 福建晋江 362200
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20203505.0464
  CLC： TP391.41
- Received：12 September 2019，
  
  Revised：16 October 2019，
  
  Accepted：16 October 2019，
  
  Published：05 May 2020
- 稿件说明：
移动端阅览
Gong-ren ZENG, Jian-min YAO, Qun YAN, et al. Hand real-time tracking method based on neural network and Kalman filter[J]. Chinese journal of liquid crystals and displays, 2020, 35(5): 464-470.
DOI：

Gong-ren ZENG, Jian-min YAO, Qun YAN, et al. Hand real-time tracking method based on neural network and Kalman filter[J]. Chinese journal of liquid crystals and displays, 2020, 35(5): 464-470. DOI： 10.3788/YJYXS20203505.0464.

摘要

针对传统的手部跟踪算法存在实时性差、识别精度低、易受环境影响等问题，提出了一种基于神经网络与卡尔曼滤波的手部实时追踪方法。该方法首先通过神经网络对视频中出现的检测目标进行定位，接着用卡尔曼滤波对目标运动进行估计，将估计的结果与下一帧图像中检测到的目标进行比对；然后对检测到的目标进行跟踪，将手部运动的轨迹实时显示。实验结果表明，该方法能够对多个手部目标实时进行追踪，并在手部运动过程中出现交叉和形变的情况下还能保持跟踪，其平均处理帧数为21.212 f/s，追踪正确率为94.88%，基本满足手部跟踪的稳定可靠、高实时性、高鲁棒性等要求。

Abstract

Aiming at the problems of poor hand-time tracking

low recognition accuracy and environmental impact

a hand tracking method based on neural network and Kalman filtering is proposed. The method firstly locates the detection target appearing in the video through the neural network

then estimates the target motion by Kalman filter

compares the estimated result with the detected target in the next frame image

and finally detects the target

tracking and displaying the trajectory of the hand movement in real time. Experiments show that the method can track multiple hand targets in real time and keep tracking when the cross and deformation occur during hand movement. The average processing frame number is 21.212 f/s

and the tracking accuracy rate is 94.88%. It basically meets the requirements of stable

reliable

high real-time and high robustness of hand tracking.

关键词

Keywords

references

WANG Q, CHEN X L, ZHANG L G, et al . Viewpoint invariant sign language recognition[C]// Proceedings of 2005 IEEE International Conference on Image Processing . Genova, Italy: IEEE, 2005: 274-281.

C W NG , S RANGANATH . Real-time gesture recognition system and application . Image and Vision Computing , 2002 . 20 ( 13-14 ): 993 - 1007 . DOI: 10.1016/S0262-8856(02)00113-0 http://doi.org/10.1016/S0262-8856(02)00113-0 .

LIPTON A J, FUJIYOSHI H, PATIL R S. Moving target classification and tracking from real-time video[C]// Proceedings of the 4 th IEEE Workshop on Applications of Computer Vision . Princeton, NJ, USA, USA: IEEE, 1998: 8-14.

林开颜 , 吴军辉 , 徐立鸿 . 彩色图像分割方法综述 . 中国图象图形学报 , 2005 . 10 ( 1 ): 1 - 10 . DOI: 10.3969/j.issn.1006-8961.2005.01.001 http://doi.org/10.3969/j.issn.1006-8961.2005.01.001 .

K Y LIN , J H WU , L H XU . A survey on color image segmentation techniques . Journal of Image and Graphics , 2005 . 10 ( 1 ): 1 - 10 . DOI: 10.3969/j.issn.1006-8961.2005.01.001 http://doi.org/10.3969/j.issn.1006-8961.2005.01.001 .

吴秋红 , 吴谨 , 朱磊 , 等 . 基于图论和FCM的图像分割算法 . 液晶与显示 , 2016 . 31 ( 1 ): 112 - 117 . http://yjyxs.com/CN/abstract/abstract9966.shtml http://yjyxs.com/CN/abstract/abstract9966.shtml .

Q H WU , J WU , L ZHU , 等 . Image segmentation algorithm based on graph theory and FCM . Chinese Journal of Liquid Crystals and Displays , 2016 . 31 ( 1 ): 112 - 117 . http://yjyxs.com/CN/abstract/abstract9966.shtml http://yjyxs.com/CN/abstract/abstract9966.shtml .

P PEURSUM , S VENKATESH , G WEST . A study on smoothing for particle-filtered 3D human body tracking . International Journal of Computer Vision , 2010 . 87 ( 1-2 ): 53 - 74 . DOI: 10.1007/s11263-009-0205-5 http://doi.org/10.1007/s11263-009-0205-5 .

SHAMAIE A, SUTHERLAND A. A dynamic model for real-time tracking of hands in bimanual movements[C]// Proceedings of the 5 th International Gesture Workshop . Genova, Italy: Springer, 2004: 172-179.

REN S Q, HE K M, GIRSHICK R, et al . Faster R-CNN: towards real-time object detection with region proposal networks[C]// Proceedings of the 28 th International Conference on Neural Information Processing Systems . Montreal, Canada: MIT Press, 2015: 91-99.

REDMON J, DIVVALA S, GIRSHICK R, et al . You only look once: unified, real-time object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas, NV, USA: IEEE, 2016: 779-788.

方明 , 孙腾腾 , 邵桢 . 基于改进YOLOv2的快速安全帽佩戴情况检测 . 光学精密工程 , 2019 . 27 ( 5 ): 1196 - 1205 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201905023 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201905023 .

M FANG , T T SUN , Z SHAO . Fast helmet-wearing-condition detection based on improved YOLOv2 . Optics and Precision Engineering , 2019 . 27 ( 5 ): 1196 - 1205 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201905023 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201905023 .

潘蓉 , 孙伟 . 基于预分割和回归的深度学习目标检测 . 光学精密工程 , 2017 . 25 ( 10s ): 221 - 227 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=CN201710598875.X http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=CN201710598875.X .

R PAN , W SUN . Deep learning target detection based on pre-segmentation and regression . Optics and Precision Engineering , 2017 . 25 ( 10s ): 221 - 227 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=CN201710598875.X http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=CN201710598875.X .

LIU W, ANGUELOV D, ERHAN D, et al . SSD: single shot MultiBox detector[C]// Proceedings of the 14th European Conference on Computer Vision . Amsterdam, The Netherlands: Springer, 2016: 21-37.

K SIMONYAN , A ZISSERMAN . Very deep convolutional networks for large-scale image recognition . ArXiv , 2014 . 1409 1556 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1080/01431161.2018.1506593 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1080/01431161.2018.1506593 .

YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[J]. ArXiv, 2015, 1511.07122.

BAMBACH S, LEE S, CRANDALL D J, et al . Lending a hand: detecting hands and recognizing activities in complex egocentric interactions[C]// Proceedings of the IEEE International Conference on Computer Vision . Santiago, Chile: IEEE, 2015: 1949-1957.

ZHAO L M, LI X, ZHUANG Y T, et al . Deeply-learned part-aligned representations for person re-identification[C]// Proceedings of the IEEE International Conference on Computer Vision . Venice, Italy: IEEE, 2017: 3239-3248.

Views

203

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fast and robust low-light image enhancement based on iterative propagation network

Improved neural network nonuniformity correction algorithm based on side window filter

FRKDNet： feature refine semantic segmentation network based on knowledge distillation

Research progress of virtual view rendering technology for light field display

Eye fatigue assessment method for naked eye 3D display based on multiple eye movements

Related Author

KONG Yan

JIANG Zhilong

XIAO Zhibo

SUN Hai-jiang

WANG Yu-qing

LI Ming-qing

FAN Run-ze

LI Dan-yang

Related Institution

School of Science， Jiangnan University

University of Chinese Academy of Sciences

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

Guiyang Aluminum-magnesium Design and Research Institute Co.Ltd.

College of Big Data and Information Engineering， Guizhou University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰