数字图像识别技术在城市燃气SCADA系统中的应用研究
|
摘要
城市燃气管网中很多表具不具备接入SCADA系统的通信能力,从而给监管带来很大的麻烦。为了解决这一问题,提出一种基于数字图像的仪表盘示数辨识方法,通过摄像头获取表盘图片,在Canny边缘检测的基础上采用八邻域连通的区域增长法自动提取出表盘区域,通过垂直及水平方向直方图分割出待识别的数字,最后通过基于特征结构的交线法对分割出的字符进行辨识。实验结果验证了算法的有效性,识别准确率高,实时性满足系统要求,为通信接口异常表具接入SCADA系统提供了一种可行的方法,从而降低了SCADA系统中监控盲区所带来的风险。
Many of the meters in city gas pipe network has no communication capabilities to access the SCADA system. Therefore it brings a lot of security risk. A numeral recognition method was proposed in this paper to solve the problem. Firstly, meter dial image was obtained through the camera, eight neighborhood connected region growing method was applied to extract dial region automatically after canny edge detection, then numeral could be extracted through vertical and horizontal histogram, and further be recognized by structural characteristics of intersection method. The experimental results verify the effectiveness of the method. And the accurate and real-time performance can meet the requirements of the system. Therefore, the feasible method reduces the risk brought by those no communication capability meters.
Many of the meters in city gas pipe network has no communication capabilities to access the SCADA system. Therefore it brings a lot of security risk. A numeral recognition method was proposed in this paper to solve the problem. Firstly, meter dial image was obtained through the camera, eight neighborhood connected region growing method was applied to extract dial region automatically after canny edge detection, then numeral could be extracted through vertical and horizontal histogram, and further be recognized by structural characteristics of intersection method. The experimental results verify the effectiveness of the method. And the accurate and real-time performance can meet the requirements of the system. Therefore, the feasible method reduces the risk brought by those no communication capability meters.
引文
[1]张宏伟.城市燃气SCADA系统中的报警管理[J].城市燃气,2015(2):10-12.
[2]John Canny.A computational approach to edge detection[J].IEEE Transactions On Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[2]John Canny.A computational approach to edge detection[J].IEEE Transactions On Pattern Analysis and Machine Intelligence,1986,8(6):679-698.