引用本文: | 乐 健,蔡 伟,靳 超,刘开培.基于图像识别技术的变电站防误操作系统的研制[J].电力自动化设备,2011,31(7): |
| LE Jian,CAI Wei,JIN Chao,LIU Kaipei.Substation anti-misoperation system based on image recognition technology[J].Electric Power Automation Equipment,2011,31(7): |
|
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。 |
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 |
DOI: |
分类号: |
基金项目: |
|
Substation anti-misoperation system based on image recognition technology |
LE Jian, CAI Wei, JIN Chao, LIU Kaipei
|
School of Electrical Engineering,Wuhan University,Wuhan 430072,China
|
Abstract: |
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. |
Key words: electric substations five-prevention system image recognition image matching anti-misoperation Hough transformation projection method neural networks |