三线结构光视觉传感器现场标定方法

邹媛媛; 李鹏飞; 左克铸

doi:10.3788/IRLA201847.0617002

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

三线结构光视觉传感器现场标定方法

邹媛媛, 李鹏飞, 左克铸

文章导航 > 红外与激光工程 > 2018 > 47(6): 617002-0617002(6)

邹媛媛, 李鹏飞, 左克铸. 三线结构光视觉传感器现场标定方法[J]. 红外与激光工程, 2018, 47(6): 617002-0617002(6). doi: 10.3788/IRLA201847.0617002

引用本文:

邹媛媛, 李鹏飞, 左克铸. 三线结构光视觉传感器现场标定方法[J]. 红外与激光工程, 2018, 47(6): 617002-0617002(6). doi: 10.3788/IRLA201847.0617002

Zou Yuanyuan, Li Pengfei, Zuo Kezhu. Field calibration method for three-line structured light vision sensor[J]. Infrared and Laser Engineering, 2018, 47(6): 617002-0617002(6). doi: 10.3788/IRLA201847.0617002

Citation:

Zou Yuanyuan, Li Pengfei, Zuo Kezhu. Field calibration method for three-line structured light vision sensor[J]. Infrared and Laser Engineering, 2018, 47(6): 617002-0617002(6). doi: 10.3788/IRLA201847.0617002

三线结构光视觉传感器现场标定方法

doi: 10.3788/IRLA201847.0617002

邹媛媛^1,2,
李鹏飞^1,2,
左克铸^1,2

1.
沈阳建筑大学机械工程学院,辽宁沈阳 110168;
2.
高档石材数控加工装备与技术国家地方联合工程实验室,辽宁沈阳 110168

基金项目:

国家自然科学基金（51405481）;中国博士后科学基金（2017M621159）;辽宁省教育厅科研项目（LJZ2016016）

详细信息

作者简介:
邹媛媛(1981-),女,副教授,博士,主要从事机器视觉、视觉测量等方面的研究。Email:yyzou@sjzu.edu.cn

中图分类号: TP212.1

Field calibration method for three-line structured light vision sensor

1.
School of Mechanical Engineering,Shenyang Jianzhu University,Shenyang 110168,China;
2.
National-Local Joint Engineering Laboratory of NC Machining Equipment and Technology of High-Grade Stone,Shenyang 110168,China

摘要: 三线结构光视觉传感器由于获取信息量大、测量速度快等特点被广泛应用于工业现场测量。为了实现传感器高精度、快速的现场标定，提出了一种基于支持向量机的三线结构光视觉传感器标定方法。首先，设计标定靶标；其次，采集靶标图像后提取特征点亚像素坐标值；再次，基于支持向量机方法建立特征点的图像坐标和三维空间坐标的映射模型；最后，将待标定点图像坐标输入映射模型，即可得到三维空间坐标，实现对三线结构光视觉传感器的直接标定。实验验证，Y轴、Z轴方向上的测量绝对误差均值分别为0.021 1 mm和0.015 0 mm，具有较高的标定精度，且该标定方法标定过程简单、快速，适合现场标定。
- 三线结构光视觉传感器 /
- 现场标定 /
- 支持向量机
Abstract: The three-line structured light vision sensor is widely used in industrial field measurement due to it has many advantages such as speedy and abundant information. In order to calibrate the three-line structured light vision sensor on-field with high accuracy and high efficiency, a new calibration method based on support vector machine was proposed. Firstly, a calibration target was designed. Secondly, calibration images were captured and feature points were identified. And then sub-pixel coordinates of feature points were extracted. Thirdly, a direct mapping model according to image coordinates and three dimension coordinates of feature points was built based on support vector machine. Finally, image coordinates of the calibration points were put into the model and their three dimension coordinates could be obtained. So the three-line structured light vision sensor could be calibrated directly. Experimental results demonstrated that this direct calibration method had high accuracy; its mean absolute error was 0.021 1 mm in Y direction and 0.015 0 mm in Z direction. It concludes that this method is easy, fast and suitable for field calibration.
- three-line structured light vision sensor /
- field calibration /
- support vector machine

[1]	Xie Zexiao, Chen Wenzhu, Chi Shukai, et al. Industrial robot positioning system based on the guidance of the structured-light vision[J]. Acta Optica Sinica, 2016, 36(10):1015001. (in Chinese)
[2]	Konov S G, Khokholikov A A, Gololobova A A. The use of structured light for a photogrammetric method of measuring surfaces having complex shape[J]. Measurement Techniques, 2015, 58(7):757-759.
[3]	Wang Li, Li Guangjun, Yang Xinyong, et al. One-site calibration of mounted parameter method for 3D mobile laser scanning[J]. Infrared and Laser Engineering, 2016, 45(11):1106005. (in Chinese)
[4]	Sung K, Lee H, Choi Y S, et al. Development of a multiline laser vision sensor for joint tracking in welding[J]. Weld Journal, 2009, 88(4):79-85.
[5]	Wang Zongyi, Li Hongwei, Li Dianpu, et al. A direct calibration method for structured light[C]//IEEE International Conference on Mechatronics and Automation, 2005:1283-1287.
[6]	Kuang Yongcong, Cui Liangchun. A new calibration method for line-structured light vision sensor based on linear scale[J]. Journal of South China University of Technology, 2016, 44(1):71-77. (in Chinese)
[7]	Trucco E, Fisher R B. Acquisition of consistent range data using local calibration[C]//IEEE International Conference on Robotics and Automation, 1994:3410-3415.
[8]	Zhang Guangjun, Wei Zhenzhong. A method of structured light based 3D vision inspection using BP neural network[J]. Chinese Journal of Scientific Instrument, 2002, 23(1):31-35. (in Chinese)
[9]	Dipanda A, Woo S, Marzani F, et al. 3D shape reconstruction in an active stereo vision system using genetic algorithms[J]. Pattern Recognition, 2003, 36(9):2143-2159.
[10]	Abhisek U. Support vector machine[J]. Computer Science, 2007, 1(3):1303-1308.
[11]	Awad M, Khanna R. Support vector regression[J]. Neural Information Processing Letters Reviews, 2007, 11(10):203-224.

[1]	黄喆, 燕庆德, 李倩, 程二静, 沈小玲, 徐叶倩. 面向直线顶管机的双屏视觉标靶标定方法与精度评价 . 红外与激光工程, 2022, 51(9): 20210933-1-20210933-8. doi: 10.3788/IRLA20210933
[2]	翟雪瑞, 任元, 王丽芬, 朱挺, 王琛. 正四面体冗余惯导全参数现场快速标定方法 . 红外与激光工程, 2022, 51(7): 20210784-1-20210784-10. doi: 10.3788/IRLA20210784
[3]	李芳丽. 监控视频中采用深度支持向量数据描述的异常检测 . 红外与激光工程, 2021, 50(9): 20210094-1-20210094-7. doi: 10.3788/IRLA20210094
[4]	杨彦伟, 张丽丽, 郝晓剑, 张瑞忠. 机器学习结合激光诱导击穿光谱技术铁矿石分类方法 . 红外与激光工程, 2021, 50(5): 20200490-1-20200490-8. doi: 10.3788/IRLA20200490
[5]	刘晓利, 何懂, 陈海龙, 蔡泽伟, 殷永凯, 彭翔. 结构光三维传感器测量网相关技术 . 红外与激光工程, 2020, 49(3): 0303007-0303007-10. doi: 10.3378/IRLA202049.0303007
[6]	左超, 张晓磊, 胡岩, 尹维, 沈德同, 钟锦鑫, 郑晶, 陈钱. 3D真的来了吗？— 三维结构光传感器漫谈 . 红外与激光工程, 2020, 49(3): 0303001-0303001-45. doi: 10.3788/IRLA202049.0303001
[7]	张东阁, 傅雨田. 基于一类支持向量机的盲元检测方法 . 红外与激光工程, 2018, 47(4): 404001-0404001(7). doi: 10.3788/IRLA201847.0404001
[8]	吴军伟, 缪玲娟, 李福胜, 沈军. 改进支持向量机的光纤陀螺温度漂移补偿方法 . 红外与激光工程, 2018, 47(5): 522003-0522003(6). doi: 10.3788/IRLA201847.0522003
[9]	李鹏, 种文艳, 马永军. 加工中心工件在机三维检测系统的光平面标定 . 红外与激光工程, 2017, 46(3): 317002-0317002(7). doi: 10.3788/IRLA201746.0317002
[10]	张文涛, 李跃文, 占平平, 熊显名. 基于太赫兹时域光谱技术与PCA-SVM的转基因大豆油鉴别研究 . 红外与激光工程, 2017, 46(11): 1125004-1125004(6). doi: 10.3788/IRLA201746.1125004
[11]	张长江, 戴李杰, 马雷鸣. 应用SVM的PM2.5未来一小时浓度动态预报模型 . 红外与激光工程, 2017, 46(2): 226002-0226002(8). doi: 10.3788/IRLA201746.0226002
[12]	张东阁, 傅雨田. 基于在线最小二乘支持向量机的变形镜建模与控制 . 红外与激光工程, 2016, 45(11): 1118007-1118007(7). doi: 10.3788/IRLA201645.1118007
[13]	刘姜伟, 黄海乐, 李五. 天绘一号卫星高分辨、多光谱相机与三线阵正视相机夹角在轨标定方法研究 . 红外与激光工程, 2015, 44(2): 662-667.
[14]	梁栋, 杨勤英, 黄文江, 彭代亮, 赵晋陵, 黄林生, 张东彦, 宋晓宇. 基于小波变换与支持向量机回归的冬小麦叶面积指数估算 . 红外与激光工程, 2015, 44(1): 335-340.
[15]	郭凯, 孙红胜, 张虎, 张玉国, 魏树弟, 孙广尉. 仿真用红外动态场景模拟器现场校准技术 . 红外与激光工程, 2014, 43(5): 1380-1384.
[16]	梁栋, 谢巧云, 黄文江, 彭代亮, 杨晓华, 黄林生, 胡勇. 最小二乘支持向量机用于时间序列叶面积指数预测 . 红外与激光工程, 2014, 43(1): 243-248.
[17]	李庆辉, 李艾华, 苏延召, 马治明. 结合FCM聚类与SVM的火焰检测算法 . 红外与激光工程, 2014, 43(5): 1660-1666.
[18]	韩军, 常波, 路邵军, 吴玲玲, 占春连. SVM 的光栅成像光谱仪图像畸变校准方法 . 红外与激光工程, 2014, 43(9): 3099-3104.
[19]	卞春江, 余翔宇, 侯晴宇, 张伟. 最小化支持向量数分类器的云检测 . 红外与激光工程, 2014, 43(6): 1818-1822.
[20]	杨远洪, 段纬倩, 高丽娟. 反射型保偏光纤温度传感器现场校准方法 . 红外与激光工程, 2012, 41(8): 2107-2111.

点击查看大图

计量

文章访问数: 370
HTML全文浏览量: 48
PDF下载量: 48
被引次数: 0

三线结构光视觉传感器现场标定方法

doi: 10.3788/IRLA201847.0617002

1. 沈阳建筑大学机械工程学院,辽宁沈阳 110168;

2. 高档石材数控加工装备与技术国家地方联合工程实验室,辽宁沈阳 110168

作者简介:
邹媛媛(1981-),女,副教授,博士,主要从事机器视觉、视觉测量等方面的研究。Email:yyzou@sjzu.edu.cn

收稿日期: 2018-01-05
修回日期: 2018-02-15
刊出日期: 2018-06-25

基金项目:

国家自然科学基金（51405481）;中国博士后科学基金（2017M621159）;辽宁省教育厅科研项目（LJZ2016016）

中图分类号: TP212.1

关键词:

摘要: 三线结构光视觉传感器由于获取信息量大、测量速度快等特点被广泛应用于工业现场测量。为了实现传感器高精度、快速的现场标定，提出了一种基于支持向量机的三线结构光视觉传感器标定方法。首先，设计标定靶标；其次，采集靶标图像后提取特征点亚像素坐标值；再次，基于支持向量机方法建立特征点的图像坐标和三维空间坐标的映射模型；最后，将待标定点图像坐标输入映射模型，即可得到三维空间坐标，实现对三线结构光视觉传感器的直接标定。实验验证，Y轴、Z轴方向上的测量绝对误差均值分别为0.021 1 mm和0.015 0 mm，具有较高的标定精度，且该标定方法标定过程简单、快速，适合现场标定。

English Abstract

Field calibration method for three-line structured light vision sensor

1. School of Mechanical Engineering,Shenyang Jianzhu University,Shenyang 110168,China;

2. National-Local Joint Engineering Laboratory of NC Machining Equipment and Technology of High-Grade Stone,Shenyang 110168,China

Received Date: 2018-01-05
Rev Recd Date: 2018-02-15
Publish Date: 2018-06-25

Keywords:

three-line structured light vision sensor /
field calibration /
support vector machine

Abstract: The three-line structured light vision sensor is widely used in industrial field measurement due to it has many advantages such as speedy and abundant information. In order to calibrate the three-line structured light vision sensor on-field with high accuracy and high efficiency, a new calibration method based on support vector machine was proposed. Firstly, a calibration target was designed. Secondly, calibration images were captured and feature points were identified. And then sub-pixel coordinates of feature points were extracted. Thirdly, a direct mapping model according to image coordinates and three dimension coordinates of feature points was built based on support vector machine. Finally, image coordinates of the calibration points were put into the model and their three dimension coordinates could be obtained. So the three-line structured light vision sensor could be calibrated directly. Experimental results demonstrated that this direct calibration method had high accuracy; its mean absolute error was 0.021 1 mm in Y direction and 0.015 0 mm in Z direction. It concludes that this method is easy, fast and suitable for field calibration.