应用于水表检定的机器视觉技术研究

Research on machine vision technology applied in water meter verification

为解决目前水表检定存在效率低、人为因素影响大等诸多问题,提出了应用机器视觉技术的水表检定系统,并重点研究实现梅花针快速定位的模板匹配算法和消除湿式水表表盘气泡的图像形态学算法。使用Harris算法预先提取梅花针模板角点,并实时提取现场图像的角点。采用部分Hausdorff距离法,实现梅花针的快速定位;利用图像形态学算法实时消除气泡影响,并完成对梅花针转动齿数的计数。实验表明,该系统在保证检定准确性的同时,可缩短检定时间,提高水表检定效率,解决了湿式水表表盘气泡对检定的不良影响,适用于各类水表的检定。

In order to solve the low efficiency and the influence of manual factors and many other problems existed in current water meter verification, the water meter verification system using machine vision technology is proposed. And the research keynote is how to realize the template matching algorithm for rapid location of plum blossom needle and the image morphological algorithm for eliminating the bubble of wet water meter dial. Harris algorithm is used to extract the comer points of the plum blossom needle template beforehand, and the corner points of the on-site image are extracted in real time. Then, the fast localization of the plum blossom needle is realized by the partial Hausdorff distance method. Finally, the effect of bubbles is eliminated by using the image morphological algorithm, and the count value of the rotating teeth of the plum blossom needle is completed. The experimental results show that the proposed system can shorten the verification time and improve the verification efficiency while ensuring the verification accuracy. The system solves the adverse effect of the bubble on the dial of the wet water meter, and it＇ s suitable for the verification of various types of water meters.