作者：鲁永杰, 王思明

作者单位：兰州交通大学自动化与电气工程学院, 甘肃 兰州 730070

关键词：目标跟踪;光流法;立体视觉;自适应滤波;遮挡;模糊控制

摘要：

为解决障碍物在三维目标跟踪中产生的遮挡问题,使用基于光流法和立体视觉的目标跟踪系统,同时结合自适应滤波方法来预测跟踪目标三维速度的期望值。采用模糊控制系统解决不同速度的耦合问题,通过计算跟踪算法与预测算法的速度差值来判断运动目标是否受到遮挡。实验结果表明:在确保91.2%识别率的前提下,该算法识别运动目标平均每帧耗时15 ms。该跟踪算法具有较好的鲁棒性和实时性。

An improved moving object tracking method

LU Yongjie, WANG Siming

School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China

Abstract: An object tracking system based on optical flow and stereo vision is used in order to solve the occlusion effect produced by obstacles in 3D object tracking, combined with adaptive filters to predict the expected 3D velocities of objects. The critical point of the system is the coupling between tracking and predictive algorithms. A fuzzy control system is proposed to solve this coupling problem between the different velocities and judging whether the moving objects are blocked by calculating the speed difference between tracking algorithm and prediction algorithm. Experimental results show this algorithm costs average 15 ms per recognition of one frame with a recognition rate at 91.2%. This tracking algorithm has better robustness and real-time ability.

Keywords: object tracking;optical flow;stereo vision;adaptive filters;occlusion;fuzzy control

2015, 41(7): 95-98  收稿日期: 2014-10-29;收到修改稿日期: 2014-12-25

基金项目: 

作者简介: 鲁永杰(1989-),男,甘肃兰州市人,硕士研究生,专业方向为图像处理。

参考文献

[1] 宋伟,纳鹏宇,刘宁宁,等. 基于双目视觉系统的运动目标跟踪算法研究[J]. 北京交通大学学报,2013,37(6):13-17.
[2] 余静,游志胜. 自动目标识别与跟踪技术研究综述[J]. 计算机应用研究,2005,22(1):12-15.
[3] 吴阳,徐立鸿,李大威,等. 一种改进的基于光流法的运动目标跟踪算法[J]. 机电一体化,2011,17(12):18-25.
[4] Parrilla E, Torregrosa J R, Riera J, et al. Fuzzy control for obstacle detection in stereo video sequences[J]. Mathematical and Computer Modelling,2011,54(7):1813-1817.
[5] 李剑峰,黄增喜,刘怡光.基于光流场估计的自适应Mean-Shift目标跟踪算法[J]. 光电子·激光,2012,23(10):1996-2002.
[6] 孙承志,熊田忠,吉顺平,等. 基于差分的光流法在目标检测跟踪中的应用[J]. 机床与液压,2010,38(14):59-62.
[7] 许晓航,肖刚,云霄,等. 复杂背景及遮挡条件下的运动目标跟踪[J]. 光电工程,2013,40(1):23-30.