改进线性外推法预估器的手势跟踪

doi:10.3969/j.issn.0255-8297.2017.01.009

应用科学学报 ›› 2017, Vol. 35 ›› Issue (1): 81-89.doi: 10.3969/j.issn.0255-8297.2017.01.009

改进线性外推法预估器的手势跟踪

姚恒, 袁敏, 秦川, 田颖

上海理工大学光电信息与计算机工程学院, 上海 200093

收稿日期:2016-03-28 修回日期:2016-04-12 出版日期:2017-01-30 发布日期:2017-01-30
作者简介:姚恒,博士,讲师,研究方向:数字图像防伪鉴定、图像识别与增强,E-mail:hyao@usst.edu.cn
基金资助:
国家自然科学基金（No.61303203）；沪江基金（No.B14002/D14002）资助

Gesture Tracking Using Improved Linear Extrapolation Predictor

YAO Heng, YUAN Min, QIN Chuan, TIAN Ying

Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received:2016-03-28 Revised:2016-04-12 Online:2017-01-30 Published:2017-01-30

摘要/Abstract

摘要：

针对动态手势识别系统手势跟踪问题，提出了一种基于改进线性外推法预估器的手势跟踪算法.该算法用前两帧的平均位移作为未来帧的位移预测，提高了预测精度；采用5点直线拟合，根据拟合直线斜率判断目标遮挡和重叠状态下的运动方向，克服了由于手势目标质心变化引起的预测位置偏离实际目标的缺陷.实验结果表明：所提出的算法能准确稳定地跟踪手势目标，平均预测偏差缩小到3.374像素，并且能在手势被遮挡和手势重叠的情况下实现有效跟踪.

关键词: 线性外推, 手势跟踪, 手势遮挡重叠, 动态手势识别系统

Abstract:

To improve accuracy of gesture tracking in dynamic gesture recognition system, a gesture tracking algorithm using an improved linear extrapolation predictor is proposed.Specifcally, to improve prediction accuracy, the algorithm uses the average displacement of two previous frames as the future-frame predictor.Besides, to deal with occlusion and hands-overlap, the target movement direction is determined based on the slope of ftting line with fve points.Thus deviation between the predicted and actual positions caused by the changing gesture centroid is reduced.Experimental results show that efciency of the proposed gesture tracking method with the average prediction deviation is reduced to 3.374 pixels.In addition, even in the case of occlusion and hands-overlap, the gesture target can also be tracked effectively.

Key words: gesture tracking, linear extrapolation, dynamic gesture recognition system, gesture occlusion and overlap

中图分类号:

TP274.2

姚恒, 袁敏, 秦川, 田颖. 改进线性外推法预估器的手势跟踪[J]. 应用科学学报, 2017, 35(1): 81-89.

YAO Heng, YUAN Min, QIN Chuan, TIAN Ying. Gesture Tracking Using Improved Linear Extrapolation Predictor[J]. Journal of Applied Sciences, 2017, 35(1): 81-89.

参考文献

[1] Rautaray S S, Agrawal A. Vision based hand gesture recognition for human computer interaction:a survey[J]. Artifcial Intelligence Review, 2015, 43(1):1-54.
[2] Hu M C, Chang M H, Wu J L, Chi L. Robust camera calibration and player tracking in broadcast basketball video[J]. IEEE Transactions on Multimedia, 2011, 13(2):266-279.
[3] 修春波,魏世安,万蓉凤. 二维联合特征模型的自适应均值漂移目标跟踪[J]. 光电子·激光,2015, 26(2):343-351. Xiu C B, Wei S A, Wan R F. CamShift target tracking based on two-dimensional joint characteristics[J]. Journal of Optoelectronics·Laser, 2015, 26(2):343-351. (in Chinese)
[4] 王守觉,蒋寓文,谭乐怡. 利用多级量化局部纹理特征的图像跟踪算法[J]. 计算机辅助设计与图形学学报,2015,27(2):208-216. Wang S J, Jiang Y W, Tan L Y. Object tracking algorithm using multi-scale local texture features[J]. Journal of Computer-Aided Design & Computer Graphics, 2015, 27(2):208-216. (in Chinese)
[5] Lien S F, Hsia K H, Su J P. Moving target tracking based on CamShift approach and Kalman flter[J]. Applied Mathematics & Information Sciences, 2015, 9(1):395-401.
[6] 王国良,刘金国. 基于粒子滤波的多自由度运动目标跟踪[J]. 光学精密工程,2011, 19(4):864-869. Wang G L, Liu J G. Moving object tracking with multi-degree-of-freedom based on particle flters[J]. Optics and Precision Engineering, 2011, 19(4):864-869. (in Chinese)
[7] 王法胜,鲁明羽,赵清杰,袁泽剑. 粒子滤波算法[J]. 计算机学报,2014, 37(8):104-107. Wang F S, Lu M Y, Zhao Q J, Yuan Z J. Particle fltering algorithm[J]. Chinese Joural of Computers, 2014, 37(8):104-107. (in Chinese)
[8] Liu P, Li W, Wang Y, Ni H. On-road multi-vehicle tracking algorithm based on an improved particle flter[J]. IET Intelligent Transport Systems, 2014, 9(4):429-441.
[9] Kwon J, Lee H S, Park F C, Lee K M. A geometric particle flter for template-based visual tracking[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 36(4):625- 643.
[10] 韩涛,吴衡,张虎龙. Kalman滤波融合优化Mean Shift的目标跟踪算法[J]. 光电工程, 2014,41(6):56-62. Han T, Wu H, Zhang H L. Target tracking algorithm based on Kalman flter and optimization mean shift[J]. Opto-electronic Engineering, 2014, 41(6):56-62. (in Chinese)
[11] Chiang C T, Tseng P H, Feng K T. Hybrid unifed Kalman tracking algorithms for heterogeneous wireless location systems[J]. IEEE Transactions on Vehicular Technology, 2012, 61(2):702-715.
[12] Marilly E, Gonguet A, Martinot O, Pain F. Gesture interactions with video:from algorithms to user evaluation[J]. Bell Labs Technical Journal, 2013, 17(4):103-118.
[13] Suk H I, Sin B K, Lee S W. Hand gesture recognition based on dynamic Bayesian network framework[J]. Pattern Recognition, 2010, 43(9):3059-3072.
[14] Argyros A A, Lourakis M I A. Real-time tracking of multiple skin-colored objects with a possibly moving camera[J]. Lecture Notes in Computer Science, 2004, 3023(3):368-379.
[15] 宋振宇,张翔宇,张磊. 一种基于加速度预估计的机动目标跟踪算法[J]. 海军航空工程学院学报,2015,30(2):101-105. Song Z Y, Zhang X Y, Zhang L. Algorithm for maneuvering target tracking with acceleration pre-estimation[J]. Journal of Naval Aeronautical and Astronautical University, 2015, 30(2):101-105. (in Chinese)
[16] Yao Y, Fu Y. Contour model-based hand-gesture recognition using the kinect sensor[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2014, 24(11):1935-1944.

改进线性外推法预估器的手势跟踪

Gesture Tracking Using Improved Linear Extrapolation Predictor

PDF

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 1

编辑推荐

Metrics

本文评价