基于特征匹配的高压断路器指示灯图像识别

Image Recognition Method of High Voltage Circuit Breaker Indicator Light Based on Feature Matching

采用视频图像的色彩特征算法对断路器分、合状态指示灯进行图像识别。将典型图片进行区域分割,针对指示灯分、合图像特点,采用6值灰度构造方法,构造图片的色彩特征,用多种环境下历史图片进行特征采集、训练,得到在线识别的特征专家知识库。最后,根据特征专家知识库,对在线视频图片进行实时分析,对比预设值发出警报。算例采用运行中的铁路牵引变电所实时图片数据,进行了断路器分、合状态的图像识别,结果表明所提方法在在线图像识别方面的可行性,具有一定实用价值。

The color feature algorithm of video image is used to recognize the on and off state indicator light of circuit breaker.A typical image is divided into regions.According to the characteristics of indicator light on and off image,a 6 values gray level construction method is used to construct the image color features.Through feature collection and training of historical images in various environments,the expert knowledge base of online recognition is obtained Finally,the online video images are analyzed in real time according to the feature expert knowledge base,and the alarm is issued by comparing the preset values..Using the real-time picture data of railway traction substation in operation,the image recognition of circuit breaker on and off state is carried out in the example.The results show that the proposed method is feasible in the on-line image recognition and has certain practical value.