变电站设备的实时状态监测对电网的安全稳定运行起着至关重要的作用。为实现复杂背景下变电站设备的快速、准确识别,提出了一种基于轻量型YOLO v5(you only look once v5)的红外图像识别方法。通过在骨干网络中引入Ghost卷积,实现网络...变电站设备的实时状态监测对电网的安全稳定运行起着至关重要的作用。为实现复杂背景下变电站设备的快速、准确识别,提出了一种基于轻量型YOLO v5(you only look once v5)的红外图像识别方法。通过在骨干网络中引入Ghost卷积,实现网络轻量化,提升检测速度;并添加基于通道间信息交互策略的注意力模块,排除无关信息,增强目标显著度;在特征融合阶段,结合自注意力的改进C3模块来增强特征捕捉能力,提高网络精度;此外,网络引入Cluster NMS(non-maximum suppression)和EIOU(efficient intersection over union)损失来加速网络收敛。在包含3类变电设备的数据集上进行测试,网络的整体识别精度达到93.80%,速度达到0.0011s/张。与4种经典网络进行比较,实验结果表明,该文方法在提升网络精度的同时将平均耗时降低5.42%,模型的储存大小减少26.38%,能够满足变电站设备识别的准确性和实时性要求,为后续变电设备的故障诊断提供条件。展开更多
Aimed at the problems of infrared image recognition under varying illumination,face disguise,etc.,we bring out an infrared human face recognition algorithm based on 2DPCA.The proposed algorithm can work out the covari...Aimed at the problems of infrared image recognition under varying illumination,face disguise,etc.,we bring out an infrared human face recognition algorithm based on 2DPCA.The proposed algorithm can work out the covariance matrix of the training sample easily and directly;at the same time,it costs less time to work out the eigenvector.Relevant experiments are carried out,and the result indicates that compared with the traditional recognition algorithm,the proposed recognition method is swift and has a good adaptability to the changes of human face posture.展开更多
文摘变电站设备的实时状态监测对电网的安全稳定运行起着至关重要的作用。为实现复杂背景下变电站设备的快速、准确识别,提出了一种基于轻量型YOLO v5(you only look once v5)的红外图像识别方法。通过在骨干网络中引入Ghost卷积,实现网络轻量化,提升检测速度;并添加基于通道间信息交互策略的注意力模块,排除无关信息,增强目标显著度;在特征融合阶段,结合自注意力的改进C3模块来增强特征捕捉能力,提高网络精度;此外,网络引入Cluster NMS(non-maximum suppression)和EIOU(efficient intersection over union)损失来加速网络收敛。在包含3类变电设备的数据集上进行测试,网络的整体识别精度达到93.80%,速度达到0.0011s/张。与4种经典网络进行比较,实验结果表明,该文方法在提升网络精度的同时将平均耗时降低5.42%,模型的储存大小减少26.38%,能够满足变电站设备识别的准确性和实时性要求,为后续变电设备的故障诊断提供条件。
基金Sponsored by the Natural Science Fund of Heilongjiang province(Grant No. F2007-13)Science and Technology Research Projects in Office of Education of Heilongjiang province(Grant No.11531034)the Heilongjiang Postdoctoral Science Foundation(Grant No.LBH-Z06054)
文摘Aimed at the problems of infrared image recognition under varying illumination,face disguise,etc.,we bring out an infrared human face recognition algorithm based on 2DPCA.The proposed algorithm can work out the covariance matrix of the training sample easily and directly;at the same time,it costs less time to work out the eigenvector.Relevant experiments are carried out,and the result indicates that compared with the traditional recognition algorithm,the proposed recognition method is swift and has a good adaptability to the changes of human face posture.