|本期目录/Table of Contents|

[1]肖永强,王海晖*,刘奥丽,等.双目实时目标三维测量实现方法的研究[J].武汉工程大学学报,2016,38(4):386-393.[doi:10. 3969/j. issn. 1674?2869. 2016. 04. 014]
 XIAO Yongqiang,WANG Haihui*,LIU Aoli,et al.Realization Method of Three Dimensional Measurement of Real-Time Target of Binocular Stereo Vision[J].Journal of Wuhan Institute of Technology,2016,38(4):386-393.[doi:10. 3969/j. issn. 1674?2869. 2016. 04. 014]
点击复制

双目实时目标三维测量实现方法的研究(/HTML)
分享到:

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
38
期数:
2016年4期
页码:
386-393
栏目:
机电工程
出版日期:
2016-08-28

文章信息/Info

Title:
Realization Method of Three Dimensional Measurement of Real-Time Target of Binocular Stereo Vision
作者:
肖永强1王海晖12*刘奥丽1王子维1章刘斌1
1. 武汉工程大学计算机科学与工程学院,湖北 武汉 430205;2. 智能机器人湖北省重点实验室(武汉工程大学),湖北 武汉 430205
Author(s):
XIAO Yongqiang1 WANG Haihui12* LIU Aoli1 WANG Ziwei1 ZHANG Liubin1
1. School of Computer Science & Technology, Wuhan Institute of Technology, Wuhan 430205, China;2. Hubei Key Laboratory of Intelligent Robot (Wuhan Institute of Technology), Wuhan 430205, China
关键词:
双目立体视觉特征点匹配三维测距
Keywords:
binocular stereo vision feature point matching 3D distance measurement
分类号:
TP242.6
DOI:
10. 3969/j. issn. 1674?2869. 2016. 04. 014
文献标志码:
A
摘要:
为了解决目标匹配困难、匹配效率低等问题,提出了一种基于双目立体视觉的实时目标特征匹配算法——绝对窗口误差最小化(CAEW). 首先,在研究摄像机基本原理后利用张氏标定法解决摄像机的标定,并对最终标定数据采用Bouguet算法进行双目立体校正;然后,利用AdaBoost迭代算法训练目标检测器实现目标检测. 将 CAEW算法与常用的尺度不变性的特征点检测和匹配(SURF)的效果评估进行比较分析,结果显示CAEW算法的效果评估能达到90%以上,这一指标有明显提高,可以很好地满足双目实时目标匹配的需求. 通过CAEW与SURF算法实验对比,进一步说明了减少不必要的全局性图像像素点处理可以提高匹配速度.
Abstract:
To improve efficiency of the target-matching, a matching algorithm based on real-time target characteristics of binocular stereo vision, namely absolute window error minimization (CAEW) was presented. Firstly, the camera calibration was realized by the Zhang’s calibration method based on the basic principle of camera, and the final data of binocular stereo calibration was tested by Bouguet algorithm. Then, the target detector was trained by AdaBoost iterative algorithm for better target detection. The evaluated effects of CAEW algorithm was compared with that of the commonly Speeded-up Robust Feature (SURF) algorithm, and the results show that the evaluated effects of CAEW algorithm achieve more than 90%, which is significantly improved, and can meet the requirement of the application of binocular real-time target matching. By comparing with the experimental results of SURF and CAEW algorithm, it demonstrates that the reduction of unnecessary operation can improve the matching speed.

参考文献/References:

[1] 李强,张钹. 一种基于图像灰度的快速匹配算法[J]. 软件学报,2006,17(2): 216-222. LI Q,ZHANG B. A fast matching algorithm based on image gray level[J]. Journal of software,2006,17(2): 216-222. [2] 罗希平,田捷. 自动指纹识别中的图像增强和细节匹配算法[J]. 软件学报,2002,13(5): 946-956. LUO X P,TIAN J. Image enhancement and minutia matching algorithms in automatic fingerprint identification system[J]. Journal of software,2002,13(5): 946-956. [3] 王宏力,贾万波. 图像匹配算法研究综述[J]. 计算机技术与应用,2008(6): 17-19. WANG H L, JIA W B. Survey of Research on Image Matching Algorithm[J]. Advances in computer technology and Applications, 2008(6):418-423.[4] 张艳珍,欧宗瑛. 一种新的摄像机线性标定方法[J]. 中国图象图形学报,2001,6(8): 727-731. ZHANG Y Z,OU Z Y. A new camera linear approach for camera calibration[J]. Journal of image and graphics,2001,6(8): 727-731. [5] TAO J,HONG Z J,WEN M H,et al. Evaluating 3D position and velocity of subject in parabolic flight experiment by use of the binocular stereo vision measurement[J]. Chinese optics letters,2010,8(6): 601-605. [6] 马颂德,张正友. 计算机理论与算法基础[M]. 北京:科学出版社,1998. [7] 刘金颂,原思聪,张庆阳.双目立体视觉中的摄像机标定技术研究[J].计算机工程与应用,2008,44(6):237-239.LIU J S, YUAN S C,ZHANG Q Y. Research on camera calibration in binocular stereo vision[J].Computer engineering & application,2008,44(6):237-239.[8] 杨明,王海晖,陈君,等. 双目标定系统精度提高的方法[J]. 武汉工程大学学报, 2012, 34(1): 69-73. YANG M,WANG H H,CHEN J, et al. Method of accuracy improvement based on binocular calibration system [J]. Journal of Wuhan institute of technology,2012,34(1): 69-73. [9] 徐磊. 摄像机标定算法研究[D]. 西安:西安电子科技大学,2011. [10] 朱谊强,张洪才,程咏梅,等. 基于Adaboost算法的实时行人检测系统[D]. 西安:西北工业大学,2006. [11] 刘洋,王海晖,向云露,等. 基于改进的Adaboost算法和帧差法的车辆检测方法[J]. 华中科技大学学报(自然科学版),2013,41(z1): 379-382. LIU Y,WANG H H,XIANG Y L,et al. Vehicle detection method based on improved adaboost algorithm and frame difference method[J]. Journal of huazhong university of science and technology(Natural science edition),2013,41 (z1): 379-382. [12] 冈萨雷斯. 数字图像处理的MATLAB实现[M]. 北京:清华大学出版社,2013. [13] 高如新,王俊孟. 基于双目视觉的目标识别与定位[J]. 河南理工大学学报(自然科学版),2014,33(4): 495-500. GAO R X,WANG J M. Target recognition and localization based on binocular vision[J]. Journal of Henan polytechnic university(natural science edition),2014, 33(4): 495-500.本文编辑:陈小平

相似文献/References:

[1]陈念,李进,王海晖,等.双目立体视觉测量系统的研究与实现[J].武汉工程大学学报,2011,(05):101.[doi:10.3969/j.issn.16742869.2011.05.026]
 CHEN Nian,LI Jin,WANG Haihui,et al.Research and implementation of measurement system based on binocular stereo vision[J].Journal of Wuhan Institute of Technology,2011,(4):101.[doi:10.3969/j.issn.16742869.2011.05.026]

备注/Memo

备注/Memo:
更新日期/Last Update: 2016-07-29