物体的旋转角度快速测量

张存; 雷俊锋; 郭勇; 朱月苓

doi:doi:10.3969/j.issn.1003-501x.2016.03.003

光电工程, 2016, 43 (3): 16, 网络出版: 2016-09-12

物体的旋转角度快速测量

The Real-time Measurement of the Rotation Angle

论文大纲

张存 ^*雷俊锋郭勇朱月苓

作者单位

武汉大学电子信息学院，武汉 430072

最大类间方差矩阵中位值实时 BRISK BRISK OTSU affine matrix the medium value real-time

摘要

针对利用图像配准测量物体的旋转角度问题 ,本文提出利用改进的 BRISK特征点求取。该方法利用 BRISK初步得到特征点后，给特征点间的汉明距离设置阈值初步筛选，以余下点对的最小汉明距离为阈值进行二次筛选得到最终的匹配点对，最后这些点对分别结合 OTSU(最大类间方差 )、仿射矩阵及特征点组成的直线斜率的中位值三种方法，计算物体旋转角度及所需时间。实验结果表明，利用二次阈值对 BRISK特征点进行筛选，配准度有了很大提升；三种方法测量角度的绝对误差基本都在 1 °以内，且消耗的时间均不超过 1 s，而且对噪声，遮挡，光照变化等有一定的鲁棒性。

Abstract

In order to get the rotation angle accurately and quickly by using the image registration, the Binary Robust Invariant Scalable Keypoints (BRISK) are improved. Firstly, we can get the origin key-points by BRISK, and set a threshold to the Hamming distance between the key-points to pick out the matching pairs. Afterwards, further screen the matching pairs by the minimum Hamming distance between them. Finally, combining the matching points respectively with OTSU, the affine matrix and feature points of the slope of the straight line the median value, the rotation angle and the time it costs are measured. Experiments show that the secondary hamming distance to get the matching pairs can improve the accuracy of the matching point, the error of rotation angle measured by these three methods is not more than 1 degree, and the time they cost is less than 1 second. Besides, it keeps certain robustness to noise, loss of outline, illumination variation and so on.

参考文献

[1] 夏群峰，彭勇刚 . 基于视觉的机器人抓取系统应用研究综述 [J].机电工程， 2014，31(6)：697-701. XIA Qunfeng，PENG Yonggang. Review on application research of robots scraping system based on visual [J]. Mechanical＆ Electrical Engineering Magazine，2014，31(6)：697-701.

[2] 耿磊，邾继贵，熊芝，等 . wMPS测角不确定度研究 [J].光电工程， 2011，38(10)：6-12. GENG Lei，ZHU Jigui，XIONG Zhi，et al. Research on Angle Measurement Uncertainty of Wmps [J]. Opto-Electronic Engineering，2011，38(10)：6-12.

[3] 周星炜，王占斌，袁一方，等 . 基于光纤干涉仪的旋转角度测量系统 [J].传感器技术， 2005，24(9)：53-55. ZHOU Xingwei，WANG Zhanbin，YUAN Yifang，et al. Rotation angle measurement system based on fiber-optic Sagnac-interferometer [J]. Journal of Transducer Technology，2005，24(9)：53-55.

[4] 白福忠，包晓艳，李义军 . 角度的图像测量法 [J].计量学报， 2007，28(4)：314-316. BAI Fuzhong，BAO Xiaoyan，LI Yijun. An Image Measuring Method for angle [J]. Acta Metrologica Sinica，2007，28(4)： 314-316.

[5] 尹程龙，张旭明，徐侃 . 基于 Zernike矩的快速图像配准算法 [J].光电工程， 2012，39(11)：103-107. YIN Chenglong，ZHANG Xuming，XU Kan. Fast matching algorithm based on Zernike [J]. Opto-Electronic Engineering， 2012，39(11)：103-107.

[6] David G Lowe. Distinctive image features from scale-invariant keypoints [J]. International Journal on Computer Vision(S1573-1405)，2004，60(2)：91-110.

[7] 朱齐丹，李科，蔡成涛，等 . 采用改进的尺度不变特征变换算法计算物体旋转角度 [J].光学精密工程， 2011，19(7)： 1669-1676. ZHU Qidan，LI Ke，CAI Chengtao，et al. Calculation of object rotation angle by improved SIFT [J]. Optics and Precision Engineering，2011，19(7)：1669-1676.

[8] 余萍，董保国 . 基于 SIFT特征匹配的电力设备图像变化参数识别 [J].中国电力， 2012，45(11)：60-64. YU Ping，DONG Baoguo. Electric power equipment images based on SIFT feature matching parameters change [J]. Electric Power，2012，45(11)：60-64.

[9] ZHANG Miaohui，HOU Yandong，HU Zhentao. Accurate object tracking based on homography matrix [C]// International Conference on Computer Science and Service System，Nanjing，China，Aug 11-13，2012：2310-2312.

[10] Stefan Leutenegger，Margarita Chli，Roland Siegwart. BRISK：Binary Robust Invariant Scalable Keypoints [C]// Proceedings of the IEEE International Conference on ComputerVision (ICCV)，Barcelona，Spain，Nov 6-13，2011：2548-2555.

[11] Lee Hsuan，Liu Chih-Yin，Lin Chih-Jui，et al. Implementation of real-time object recognition system for home-service robot by integrating SURF and BRISK [C]// Conference Proceedings - 2014 International Conference on System Science and Engineering，ICSSE，Shanghai，China，July 11-13，2014：273-278.

[12] 索春宝，杨东清，刘云鹏 . 多种角度比较 SIFT、SURF、BRISK、ORB、FREAK算法 [J].北京测绘， 2014(4)：23-26. SUO Chunbao，YANG Dongqing，LIU Yunpeng. Comparing SIFT、SURF、BRISK、ORB and FREAK in some Different Perspectives [J]. Beijing Surverying and Mapping，2014(4)：23-26.

[13] 牛津图像库 . Oxford.Visual Geometry Group-Affine Covariant Regions Dataset [EB/OL]. 2014-02-10.

[14] 图像处理标准图像库 . http：//www.datatang.com/datares/go.aspx dataid=604557 [EB/OL]. 2014-06-05.

[15] OTSU N. A threshold selection method from gray-level histo-gram [J]. IEEE Transaction on Systems Man and Cybernetic(S1083-4427)，1979，9(1)：62-66.

[16] Elmar Mair，Gregory D Hager，Darius Burschka. Adaptive and generic corner detection based on the accelerated segment test [C]// Proceeding of the European Conference on Computer Vision(ECCV)，Heraklion，Crete，Greece，September 5-11， 2010：183-196.

张存, 雷俊锋, 郭勇, 朱月苓. 物体的旋转角度快速测量[J]. 光电工程, 2016, 43(3): 16. ZHANG Cun, LEI Junfeng, GUO Yong, ZHU Yueling. The Real-time Measurement of the Rotation Angle[J]. Opto-Electronic Engineering, 2016, 43(3): 16.

物体的旋转角度快速测量

关于本站 Cookie 的使用提示

全站搜索

物体的旋转角度快速测量

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索