摘要
研制了一种基于图像识别技术的变电站误操作系统。利用便携式图像捕获设备获取当前工作间隔标志牌的实时图像,并用于判断工作人员是否走错间隔。给出了该系统的整体结构和工作流程,详细介绍了采用Hough变换来检测标志牌边框,采用投影法进行标志牌字符分割以及利用神经网络法进行图像匹配技术的原理和实现方法。通过实验和现场测试验证了该系统的有效性和工程实用性。该系统能与五防系统结合以进一步提高变电站操作安全性。
A substation anti-misoperation system based on image recognition technology is proposed.The signboard image of operating bay is captured by portable camera in real time,based on which it is determined whether the working staff has accessed to the proper bay.The framework and work flow of the whole system are given,and the principle and implementation of the signboard border detection by Hough transformation,the signboard character partition by projection method and the image matching by artificial neural networks are introduced.Its effectiveness and applicability are verified by lab experiments and site tests.Cooperated with the five-prevention system,the proposed anti-misoperation system further improves the safety of substation operation.
出处
《电力自动化设备》
EI
CSCD
北大核心
2011年第7期131-135,共5页
Electric Power Automation Equipment
关键词
变电站
五防系统
图像识别
图像匹配
防误操作
HOUGH变换
投影法
神经网络
electric substations
five-prevention system
image recognition
image matching
anti-misoperation
Hough transformation
projection method
neural networks
