基于无人机的电力传输线山火灾害监测技术研究
|
摘要
对电力传输线山火灾害进行检测能够保证电能的正常传输。针对当前电力传输线山火灾害监测方法存在的监测的及时性较差,监测的可靠性较低,无法准确对火灾发生点进行定位的问题,提出一种基于无人机的电力传输线山火灾害监测方法,将RGB颜色概率模型引入到基于RGB和HSI的综合火焰颜色模型中,并根据火焰能量变化和能量闪烁特点以及面积变化率计算结果,对电力传输线图像中疑似火焰区域进行分割。在此基础上,通过主分量分析方法提取无人机采集电力传输线山火灾害监测图像中信号,确定采集图像的特征值,构建电力传输线山火灾害的主分量分析频谱,实现火焰信号判别。并利用哨兵金字塔对主分量分析频谱中烟雾的运动目标进行提取,根据火焰信号的判别结果和烟雾目标的提取结果,实现基于无人机的电力传输线山火灾害监测。实验结果表明,所提方法能够及时对电力传输线山火灾害进行监测,且监测的可靠度较高,对火灾发生点定位的精确度较高。
The detection of mountain fire disasters on power transmission lines can ensure the normal transmission of electrical energy.Aiming at the problem that the current power transmission line mountain fire disaster monitoring method has poor monitoring timeliness,low detection reliability and unable to accurately locate the fire occurrence point,a method for monitoring the mountain fire disaster based on the UAV is proposed.The RGB color probability model is introduced into the integrated flame color model based on RGB and HSI,and the suspected flame region segmentation is realized according to the change of flame energy and energy flicker and the area change rate.On this basis,the principal component analysis method is used to extract the signals in the mountain fire disaster monitoring image of the UAV collecting power transmission line,determine the characteristic value of the captured image,construct the principal component analysis spectrum of the mountain fire disaster of the power transmission line,and realize the flame signal discrimination.The Sentinel Pyramid is used to extract the moving target of the smoke in the Principal Component Analysis Spectrum.According to the discriminating result of the flame signal and the extraction result of the smoke target,the UAV-based power transmission line mountain fire disaster monitoring is realized.The delay results show that the proposed method can monitor the mountain fire disaster of the power transmission line in time,and the reliability of the monitoring is high,and the accuracy of the location of the fire occurrence is high.
The detection of mountain fire disasters on power transmission lines can ensure the normal transmission of electrical energy.Aiming at the problem that the current power transmission line mountain fire disaster monitoring method has poor monitoring timeliness,low detection reliability and unable to accurately locate the fire occurrence point,a method for monitoring the mountain fire disaster based on the UAV is proposed.The RGB color probability model is introduced into the integrated flame color model based on RGB and HSI,and the suspected flame region segmentation is realized according to the change of flame energy and energy flicker and the area change rate.On this basis,the principal component analysis method is used to extract the signals in the mountain fire disaster monitoring image of the UAV collecting power transmission line,determine the characteristic value of the captured image,construct the principal component analysis spectrum of the mountain fire disaster of the power transmission line,and realize the flame signal discrimination.The Sentinel Pyramid is used to extract the moving target of the smoke in the Principal Component Analysis Spectrum.According to the discriminating result of the flame signal and the extraction result of the smoke target,the UAV-based power transmission line mountain fire disaster monitoring is realized.The delay results show that the proposed method can monitor the mountain fire disaster of the power transmission line in time,and the reliability of the monitoring is high,and the accuracy of the location of the fire occurrence is high.
引文
[1] 周泊龙,宋英磊,俞孟蕻.基于图像处理的舰船火灾烟雾检测技术研究[J].舰船科学技术,2016,38(9):111-115.
[2] 周凤.基于证据理论和神经网络的烟雾图像检测[J].现代电子技术,2017,40(7):55-58.
[3] 赵景波,唐勇伟,张磊.基于改进小波变换的故障电弧检测方法的研究[J].电机与控制学报,2016,20(2):90-97.
[4] 刘梅梅,俞峰,徐培龙.基于物联网技术的电气火灾远程监控方法研究及应用[J].自动化与仪器仪表,2017,(6):155-156.
[5] 陈艳君,王智勇,郭凤仪,等.基于Wigner-Hough变换的栓接电缆接头松动故障检测[J].计算机工程,2016,42(8):294-299.
[6] 段锁林,杨可,毛丹,等.基于模糊证据理论算法在火灾检测中的应用[J].计算机工程与应用,2017,53(5):231-235.
[7] 朱思思,丁德红,陈朝迎,等.基于图像处理的森林火灾识别方法研究[J].红外技术,2016,38(5):440-446.
[8] 王媛彬,胡永才.低照度室内烟雾的计算机视觉检测方法[J].消防科学与技术,2017,36(4):493-496.
[9] 焦斌亮,董雪.基于非参数特征提取的早期林火烟雾检测[J].光学技术,2016,42(1):20-23.
[10] 李晨东,韩秀玲.农业温室大棚的火灾检测算法研究[J].电子设计工程,2017,25(13):32-35.
[11] 仲亭玉,刘文萍,刘鹏举.基于分数阶微分视频融合的森林烟火检测算法[J].北京林业大学学报,2017,39(3):24-31.
[12] 王慧,宋宇宁.D-S证据理论在火灾检测中的应用[J].中国安全科学学报,2016,26(5):19-23.
[13] 方杰,周庆标.Markov链代理模型结合WSN的火灾检测和监控[J].控制工程,2017,24(1):58-64.
[14] 朱磊.基于图像增强与多特征的森林火灾烟雾检测算法[J].消防科学与技术,2018,(2):225-228.
[15] 李振东,陈华寿,徐玉凤.直流系统交流窜电故障类型及检测方法[J].自动化与仪器仪表,2017,(2):20-22.
[2] 周凤.基于证据理论和神经网络的烟雾图像检测[J].现代电子技术,2017,40(7):55-58.
[3] 赵景波,唐勇伟,张磊.基于改进小波变换的故障电弧检测方法的研究[J].电机与控制学报,2016,20(2):90-97.
[4] 刘梅梅,俞峰,徐培龙.基于物联网技术的电气火灾远程监控方法研究及应用[J].自动化与仪器仪表,2017,(6):155-156.
[5] 陈艳君,王智勇,郭凤仪,等.基于Wigner-Hough变换的栓接电缆接头松动故障检测[J].计算机工程,2016,42(8):294-299.
[6] 段锁林,杨可,毛丹,等.基于模糊证据理论算法在火灾检测中的应用[J].计算机工程与应用,2017,53(5):231-235.
[7] 朱思思,丁德红,陈朝迎,等.基于图像处理的森林火灾识别方法研究[J].红外技术,2016,38(5):440-446.
[8] 王媛彬,胡永才.低照度室内烟雾的计算机视觉检测方法[J].消防科学与技术,2017,36(4):493-496.
[9] 焦斌亮,董雪.基于非参数特征提取的早期林火烟雾检测[J].光学技术,2016,42(1):20-23.
[10] 李晨东,韩秀玲.农业温室大棚的火灾检测算法研究[J].电子设计工程,2017,25(13):32-35.
[11] 仲亭玉,刘文萍,刘鹏举.基于分数阶微分视频融合的森林烟火检测算法[J].北京林业大学学报,2017,39(3):24-31.
[12] 王慧,宋宇宁.D-S证据理论在火灾检测中的应用[J].中国安全科学学报,2016,26(5):19-23.
[13] 方杰,周庆标.Markov链代理模型结合WSN的火灾检测和监控[J].控制工程,2017,24(1):58-64.
[14] 朱磊.基于图像增强与多特征的森林火灾烟雾检测算法[J].消防科学与技术,2018,(2):225-228.
[15] 李振东,陈华寿,徐玉凤.直流系统交流窜电故障类型及检测方法[J].自动化与仪器仪表,2017,(2):20-22.