Study on Detecting Method of Deflection Angle of C-shaped Hook for Steel Wire Binding Machine
-
摘要: 本文提出基于单目视觉的钢丝捆扎机C形钩偏转角度检测方法,通过在C形钩表面适当部位粘贴红色矩形标志,利用单目相机检测获得图像并通过图像处理技术获取红色矩形图轮廓形状作为靶标,最后将靶标偏转模式进行分类并建立相应偏转模式的数学模型,从而实现对靶标垂直倾角和靶标水平倾角的检测。检测方法具有较高的计算效率和准确度且容易编程实现,以高精度三坐标测量机为参考基准的实验表明该检测方法的测量精度在0.6°以内,满足车间现场C形钩偏转角度检测精度低于2°的技术要求。Abstract: Monocular vision based method is proposed for the on-line angle detection of C-shaped hook. Firstly, a red rectangle mark is pasted on the proper position of surface of the C-shaped hook, and then the image processing technique is employed to obtain the rectangle contour shape of the target from the videos. Finally, the models for target deflection mode are built to realize the measurement of the horizontal and vertical angles. The presnt method has high computational efficiency and accuracy, and the error is below 0.6° comparing with the results of three-coordinates measuring machine. It satisfies the accuracy requirement of the applications in the online detection of the angle of C-shaped hook of the steel wire binding machine.
-
表 1 垂直偏转角度检测结果对比
(°) 序号 三坐标测量机 本文检测方法 绝对误差 1 3.401 4 3 0.401 4 2 6.471 5 6 0.471 5 3 14.303 6 14 0.303 6 4 16.775 1 17 0.224 9 5 24.239 1 24 0.239 1 6 −4.761 4 −5 0.238 6 7 −8.214 4 −8 0.214 4 8 −13.447 3 −13 0.447 3 9 −18.753 7 −19 0.246 3 10 −28.976 8 −29 0.023 2 表 2 水平偏转角度检测结果对比
(°) 序号 三坐标测量机 本文检测方法 绝对误差 1 2.301 4 2.801 0 0.499 6 2 4.677 5 4.947 6 0.270 1 3 9.547 8 9.900 6 0.352 8 4 15.224 7 15.758 1 0.533 4 5 24.010 7 24.601 8 0.591 1 6 −1.299 8 −1.668 1 0.368 3 7 −7.344 7 −7.864 9 0.520 2 8 −13.640 2 −14.204 5 0.564 3 9 −21.777 9 −22.269 6 0.491 7 10 −26.511 6 −27.017 0 0.505 4 -
[1] 袁清珂, 伍财生. 钢丝捆扎机夹持机构有限元分析[J]. 机械设计与制造, 2016,(3): 217-219, 223 doi: 10.3969/j.issn.1001-3997.2016.03.059Yuan Q K, Wu C S. Finite element analysis on steel strapping clamping mechanism[J]. Machinery Design & Manufacture, 2016,(3): 217-219, 223 (in Chinese doi: 10.3969/j.issn.1001-3997.2016.03.059 [2] 孙国栋, 赵大兴.机器视觉检测理论与算法[M].北京:科学出版社, 2015Sun G D, Zhao D X. Theory and algorithm of machine vision detection[M]. Beijing: Science Press, 2015 (in Chinese) [3] 蔺小军, 单晨伟, 王增强, 等. 航空发动机叶片型面三坐标测量机测量技术[J]. 计算机集成制造系统, 2012, 18(1): 125-131Lin X J, Shan C W, Wang Z Q, et al. Measurement techniques of coordinate measuring machine for blade surface of aero-engine[J]. Computer Integrated Manufacturing Systems, 2012, 18(1): 125-131 (in Chinese [4] 丁洵, 赵前程, 王宪, 等. 结构光三维角度测量系统位姿参数优化研究[J]. 河北科技大学学报, 2015, 36(5): 467-473 doi: 10.7535/hbkd.2015yx05004Ding X, Zhao Q C, Wang X, et al. Posture parameters optimization of a structured light 3D angle measuring system[J]. Journal of Hebei University of Science and Technology, 2015, 36(5): 467-473 (in Chinese doi: 10.7535/hbkd.2015yx05004 [5] 南方. 基于线结构光的方矩形钢管弯角检测技术的研究[D].天津: 天津理工大学, 2018Nan F. Research on the bending angle detection of rectangular steel technology based on line-structured light[D]. Tianjin: Tianjin University of Technology, 2018 (in Chinese) [6] 周科杰, 冯常. 基于双目视觉的三维测量技术研究[J]. 计算机测量与控制, 2019, 27(1): 22-25Zhou K J, Feng C. Three-dimensional measurement technology based on binocular vision[J]. Computer Measurement & Control, 2019, 27(1): 22-25 (in Chinese [7] 王振宇, 李荣华, 薛豪鹏, 等. 双目视觉辅助植牙的位姿测量引导系统[J]. 大连交通大学学报, 2019, 40(3): 72-77Wang Z Y, Li R H, Xue H P, et al. Binocular vision-based pose measurement guidance system for aiding dental implant[J]. Journal of Dalian Jiaotong University, 2019, 40(3): 72-77 (in Chinese [8] 黄松梅, 毕远伟, 刘殿通, 等. 双目立体视觉非接触式测量研究[J]. 烟台大学学报, 2017, 30(4): 323-327Huang S M, Bi Y W, Liu D T, et al. Non-contact measurement with binocular stereo vision[J]. Journal of Yantai University , 2017, 30(4): 323-327 (in Chinese [9] Mittal M, Verma A, Kaur I, et al. An efficient edge detection approach to provide better edge connectivity for image analysis[J]. IEEE Access, 2019, 7: 33240-33255 doi: 10.1109/ACCESS.2019.2902579 [10] Dollár P, Zitnick C L. Structured forests for fast edge detection[C]//2013 IEEE International Conference on Computer Vision. Sydney: IEEE, 2014. [11] 王楚, 王亚刚. 基于拟合的亚像素边缘检测的算法比较[J]. 软件导刊, 2018, 17(2): 60-62, 67Wang C, Wang Y G. Comparison of algorithms for sub-pixel edge detection based on fitting[J]. Software Guide, 2018, 17(2): 60-62, 67 (in Chinese [12] 高美欢, 刘玉梅, 王刚. 基于MATLAB的图像边缘检测算法的比较与分析[J]. 北京测绘, 2018, 32(1): 48-51Gao M H, Liu Y M, Wang G. The analysis and comparison based on MATLAB edge detection algorithm[J]. Beijing Surveying and Mapping, 2018, 32(1): 48-51 (in Chinese [13] 王立, 常青, 张科, 等. Radon变换在低信噪比图像中的线段检测[J]. 红外与激光工程, 2003, 32(2): 163-166 doi: 10.3969/j.issn.1007-2276.2003.02.014Wang L, Chang Q, Zhang K, et al. Radon transform for line segment detection in low SNR image[J]. Infrared and Laser Engineering, 2003, 32(2): 163-166 (in Chinese doi: 10.3969/j.issn.1007-2276.2003.02.014 [14] 侯彪, 刘芳, 焦李成. 基于脊波变换的直线特征检测[J]. 中国科学(E辑), 2003, 46(21): 141-152Hou B, Liu F, Jiao L C. Linear feature detection based on ridgelet[J]. Science in China (Series E), 2003, 46(21): 141-152 (in Chinese [15] 贾晓丹, 李文举, 王海姣. 一种新的基于Radon变换的车牌倾斜校正方法[J]. 计算机工程与应用, 2008, 44(3): 245-248 doi: 10.3778/j.issn.1002-8331.2008.03.077Jia X D, Li W J, Wang H J. Novel approach for vehicle license plate tilt correction based on Radon transform[J]. Computer Engineering and Applications, 2008, 44(3): 245-248 (in Chinese doi: 10.3778/j.issn.1002-8331.2008.03.077 [16] 张振威, 苏燕辰. 基于M-HSI和像素偏移法的车牌定位[J]. 计算机工程与设计, 2018, 39(11): 3576-3583Zhang Z W, Su Y C. Location method for license plate based on M-HSI and pixel offset[J]. Computer Engineering and Design, 2018, 39(11): 3576-3583 (in Chinese