基于DBN图像识别的机房巡检系统设计研究
|
摘要
针对电力系统信息化问题提出了一套智能化机房巡检系统,硬件结构包括轨道车装置、云台及工业相机等,软件系统基于Windows平台进行开发,采用B/S三层架构。鉴于服务器信号灯本身较小并发光,且在一幅图像中往往分布有多个多种状态的信号灯等问题,给出了一种新的更加有效的信号灯图像特征——RGB极大比值(RGBMR)的提取算法。运用深度置信网络(DBN)对信号灯图像进行评估识别,RGBMR特征数据的一部分用于DBN模型的训练,另一部分则用于测试。大量的实验分析,以及与图像HSV空间特征和BPNN网络识别效果的对比研究证明,所提算法能更准确地识别信号灯状态图像,该系统能有效地应用于机房巡检中。
Aiming at the informationization of power system, a set of intelligent server inspection system is presented. The hardware includes rail car device, cloud terrace and industrial camera etc. The software system is developed based on Windows platform and is of B/S three-layer architecture. In view of the fact that the server signal light is small and shine, and there always distributed with a plurality of various state lights in a single image and other issues, a new and more efficient abstract algorithm for signal light image feature-RGB maximum ratio(RGBMR) is put forward. Then a deep belief network( DBN) is used to recognize the images, a part of RGBMR data is used for training the DBN model, the other part is for testing. A series of experiment analysis and the comparative study on image HSV spatial features and BPNN network recognition prove that the proposed algorithm can identify the signal light state images more accurately, and the system can be effectively applied to computer room inspection.
Aiming at the informationization of power system, a set of intelligent server inspection system is presented. The hardware includes rail car device, cloud terrace and industrial camera etc. The software system is developed based on Windows platform and is of B/S three-layer architecture. In view of the fact that the server signal light is small and shine, and there always distributed with a plurality of various state lights in a single image and other issues, a new and more efficient abstract algorithm for signal light image feature-RGB maximum ratio(RGBMR) is put forward. Then a deep belief network( DBN) is used to recognize the images, a part of RGBMR data is used for training the DBN model, the other part is for testing. A series of experiment analysis and the comparative study on image HSV spatial features and BPNN network recognition prove that the proposed algorithm can identify the signal light state images more accurately, and the system can be effectively applied to computer room inspection.
引文
[1]易健翔,秦肖臻,汪秉文.基于WSN的电力信息机房监测系统的设计[J].计算机与数字工程,2013,41(1):135-137.
[2]陈潜,刘云,高利娟.基于嵌入式Linux的机房远程监测系统研究[J].微计算机应用,2011,32(6):60-65.
[3] Choi J,Ahn B T,Kweon I S. Crosswalk and traffic light detection via integral framework[C]//2013 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision. 2013:309-312.
[4] Yu C H,Huang C,Lang Y. Traffic light detection during day and night conditions by a camera[C]//Proceedings of 2010IEEE 10th International Conference on Signal Processing.2010:821-824.
[5] Diaz-Cabrera M,Cerri P,Sanchez-Medina J. Suspended traffic lights detection and distance estimation using color features[C]//2012 15th International IEEE Conference on Intelligent Transportation Systems. 2012:1315-1320.
[6]周宣汝,袁家政,刘宏哲,等.基于HOG特征的交通信号灯实时识别算法研究[J].计算机科学,2014,41(7):313-317.
[7]蔡自兴,谷明琴.城市环境中交通信号灯准确识别与状态估计[J].控制与决策,2014,29(1):163-167.
[8] Salti S,Petrelli A,Tombari F,et al. Traffic sign detection via interest region extraction[J]. Pattern Recognition, 2015,48(4):1039-1049.
[9]侣君淑,朱文兴,沙永贺.复杂背景下的交通信号灯综合识别方法[J].山东大学学报(工学版),2014,44(2):64-68.
[10] Yin A,Lu J C,Dai Z X,et al. Isomap and deep belief network-based machine health combined assessment model[J]. Strojniski vestnik-Journal of Mechanical Engineering,2016,62(12):740-750.
[11] Guo J, Chen Y, Sun B N. Experimental study of structural damage identification based on WPT and coupling NN[J].Journal of Zhejiang University-Science A,2005,6(7):663-669.
[12] Tran V T,AlThobiani F,Ball A. An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks[J]. Expert Systems with Applications,2014,41(9):4113-4122.
[2]陈潜,刘云,高利娟.基于嵌入式Linux的机房远程监测系统研究[J].微计算机应用,2011,32(6):60-65.
[3] Choi J,Ahn B T,Kweon I S. Crosswalk and traffic light detection via integral framework[C]//2013 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision. 2013:309-312.
[4] Yu C H,Huang C,Lang Y. Traffic light detection during day and night conditions by a camera[C]//Proceedings of 2010IEEE 10th International Conference on Signal Processing.2010:821-824.
[5] Diaz-Cabrera M,Cerri P,Sanchez-Medina J. Suspended traffic lights detection and distance estimation using color features[C]//2012 15th International IEEE Conference on Intelligent Transportation Systems. 2012:1315-1320.
[6]周宣汝,袁家政,刘宏哲,等.基于HOG特征的交通信号灯实时识别算法研究[J].计算机科学,2014,41(7):313-317.
[7]蔡自兴,谷明琴.城市环境中交通信号灯准确识别与状态估计[J].控制与决策,2014,29(1):163-167.
[8] Salti S,Petrelli A,Tombari F,et al. Traffic sign detection via interest region extraction[J]. Pattern Recognition, 2015,48(4):1039-1049.
[9]侣君淑,朱文兴,沙永贺.复杂背景下的交通信号灯综合识别方法[J].山东大学学报(工学版),2014,44(2):64-68.
[10] Yin A,Lu J C,Dai Z X,et al. Isomap and deep belief network-based machine health combined assessment model[J]. Strojniski vestnik-Journal of Mechanical Engineering,2016,62(12):740-750.
[11] Guo J, Chen Y, Sun B N. Experimental study of structural damage identification based on WPT and coupling NN[J].Journal of Zhejiang University-Science A,2005,6(7):663-669.
[12] Tran V T,AlThobiani F,Ball A. An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks[J]. Expert Systems with Applications,2014,41(9):4113-4122.