作者：张浩钰, 刘顺, 朱萍玉

作者单位：广州大学机械与电气工程学院，广东 广州 510006

关键词：机器视觉;分布式传感光纤;边缘检测;路径提取;高斯线法

摘要：

高精度分布式光纤传感技术具有超高空间分辨率，可用于高应变梯度的结构形变测量。针对表贴式分布式传感光纤应变监测数据重构中的测点坐标偏差问题，提出一种基于高斯线检测的传感光纤测点坐标序列提取方法。首先利用传感光纤在物体表面所形成的高度差借助方形无影光源从侧面照明提升光纤在物体表面的区分度，采用基于Canny算法的亚像素边缘检测技术获取传感光纤目标区域，并筛选特性去除干扰边缘，最后由高斯线检测方法提取光纤中心路径，进而分段获得实际传感光纤测点坐标值。据实验表明，该文方法能有效去除粘胶等噪点准确检测平面传感光纤，并对其非规则曲线路径进行重构。

Extraction method for irregular plane path of sensing fiber with Gaussian line method
ZHANG Haoyu, LIU Shun, ZHU Pingyu
School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, China
Abstract: High-precision distributed fiber optic sensing technology with ultra-high spatial resolution can be used for structural deformation measurements with high strain gradients. In order to address the problem of the deviation of measurement point coordinates in the reconstruction of surface-mounted distributed sensing fiber strain monitoring data, a Gaussian line-detection-based method is proposed to extract the coordinate sequence of sensing fiber measurement points. Firstly, the height difference formed by the sensing fiber on the object surface is used to enhance the differentiation of the fiber on the object surface with the help of a square shadowless light source from the side, and the sub-pixel edge detection technique based on Canny algorithm is used to obtain the target area of the sensing fiber, and the interference edge is removed by the screening feature. According to the experiments, the method in this paper can effectively remove the noise such as sticky glue to accurately detect the planar sensing fiber and reconstruct its non-regular curve path.
Keywords: machine vision;distributed sensing fiber;edge detection;path extraction;Gaussian line method
2022, 48(12):15-21  收稿日期: 2022-05-03;收到修改稿日期: 2022-06-29
基金项目: 广东省自然科学基金项目(2021A1515010698)；广州大学全日制研究生基础创新项目资助(2020GDJC-M20)
作者简介: 张浩钰(1997-),男,江西新余市人,硕士研究生,专业方向为机器视觉
参考文献
[1] 章征林, 高磊, 孙阳阳, 等. 分布式光纤传感器应变传递规律研究[J]. 中国激光, 2019, 46(4): 285-293
[2] JIAO T, ZHOU Z. An optical-electrical co-sensing tape for cross-sectional deformation monitoring of shield tunnels[J]. Tunnelling and Underground Space Technology, 2021(117): 104148
[3] 何宁, 马桂珍, 何斌, 等. 基于分布式光纤监测技术的板桩码头试验研究[J]. 水利水运工程学报, 2021(4): 85-91
[4] ZHU Z C, CHENG W C, HAI T B, et al. An integration method using distributed optical fiber sensor and Auto-Encoder based deep learning for detecting sulfurized rust self-heating of crude oil tanks[J]. Journal of Loss Prevention in the Process Industries, 2021(74): 104623
[5] ZHU P Y, WANG Y T, WANG S B, et al. Measuring the two-dimensional temperature profile of carbon fiber reinforced polymers during drilling using distributed fiber sensing[J]. Journal of Lightwave Technology, 2019, 37(18): 4687-4696
[6] 李建军, 史志晖, 崔桂梅, 等. 基于边缘矢量的镰刀弯在线检测方法研究[J]. 中国测试, 2022, 48(1): 14-19
[7] 刘桂雄, 张瑜, 蔡柳依婷. 机器视觉检测图像拼接融合技术研究进展[J]. 中国测试, 2020, 46(1): 1-6
[8] 陈家焱, 景利孟, 洪涛, 等. 基于机器视觉的漆包线线径在线检测系统设计[J]. 中国测试, 2019, 45(12): 119-125
[9] 周国栋. 一种基于机器视觉的表面缺陷快速检测方法[J]. 机电工程术, 2021, 50(8): 42-44
[10] 杨小艳. 基于图像处理技术的包装表面缺陷检测[J]. 微型电脑应用, 2021, 37(8): 63-66
[11] 邬依林, 萧华希, 李万益, 等. 太阳能电池背面电极的分割与缺陷检测[J]. 中山大学学报(自然科学版)(中英文), 2022, 61(4): 160-169
[12] WIN M, BUSHROA A R, HASSAN M A, et al. A contrast adjustment thresholding method for surface defect detection based onmesoscopy[J]. IEEE Transactions on Industrial Informatics, 2015, 11(3): 642-649
[13] DHARA A K, MUKHOPADHYAY S, KHANDELWAL N. Computer-Aided detection and analysis of pulmonary nodule from CT images: A survey[J]. IETE Technical Review, 2012, 29(4): 265-275
[14] 张铮, 徐超, 任淑霞, 等. 数字图像处理与机器视觉[M]. 北京: 人民邮电出版社, 2015.