基于深度学习低图像要求的继电保护压板状态自动识别方法
CSTR:
作者:
作者单位:

国网天津市电力公司滨海供电分公司

基金项目:

国网天津市电力公司滨海供电分公司科技项目,名称:基于移动终端的继电保护智能运维应用设计开发项目,(SGTJBH00YJXX1903437)


Automatic recognition method of relay protection pressing plate state based on deep learning and low image requirements
Author:
Affiliation:

Binhai power supply branch of State Grid Tianjin Electric Power Company

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [21]
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    继电保护装置压板布局方式逐步向简约化,标准化进行转变,客观上为压板智能化巡视提供了条件,但受限于实际场景,往往无法提供足够大小和分辨率的压板图像用于压板识别。本文提出了一种通过图像增强网络和目标识别网络两种深度神经网络的协同学习来识别低分辨率保护压板图像的方法。所提出的图像增强网络使用来自目标识别网络的协作学习信号,将极低分辨率的图像增强为更清晰和信息更丰富的图像。以及具有高分辨率图像训练权重的目标识别网络主动参与图像增强网络的学习。它还利用图像增强网络的输出作为增强学习数据,以提高其对极低分辨率对象的识别性能。通过在各种低分辨率图像基准数据集上的实验,验证了该方法能够提高保护压板图像重建和分类性能。

    Abstract:

    The layout of the pressure plate of the relay protection device is gradually simplified and standardized, which objectively provides conditions for the intelligent inspection of the pressure plate. However, limited by the actual scene, it is often impossible to provide a pressure plate image of sufficient size and resolution for pressure plate recognition. This paper proposes a method to identify low-resolution protective platen images through collaborative learning of two deep neural networks, image enhancement network and target recognition network. The proposed image enhancement network uses collaborative learning signals from the target recognition network to enhance extremely low-resolution images into clearer and more informative images. And the target recognition network with high-resolution image training weight actively participates in the learning of the image enhancement network. It also uses the output of the image enhancement network as enhanced learning data to improve its recognition performance for very low-resolution objects. Through experiments on various low-resolution image benchmark data sets, it is verified that this method can improve the performance of the protection platen image reconstruction and classification.

    参考文献
    [1] 郑胤,陈权崎,章毓晋.深度学习及其在目标和行为识别中的新进展[J].中国图象图形学报,2014,19(02):175-184.
    [2] Zheng Yin, Chen Quanqi, Zhang Yujin. Deep learning and its new progress in target and behavior recognition[J]. Journal of Image and Graphics, 2014, 19(02): 175-184.
    [3] [2] 曲景影,孙显,高鑫.基于CNN模型的高分辨率遥感图像目标识别[J].国外电子测量技术,2016,35(08):45-50.
    [4] Qu Jingying, Sun Xian, Gao Xin. High-resolution remote sensing image target recognition based on CNN model[J]. Foreign Electronic Measurement Technology, 2016, 35(08): 45-50.
    [5] [3] 张文达,许悦雷,倪嘉成.基于多尺度分块卷积神经网络的图像目标识别算法[J].计算机应用,2016,36(04):1033-1038.
    [6] Zhang Wenda, Xu Yuelei, Ni Jiacheng. Image target recognition algorithm based on multi-scale block convolutional neural network[J].Computer Applications, 2016, 36(04): 1033-1038.
    [7] [4] K. He, X. Zhang, S. Ren. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification[C].2015 IEEE International Conference on Computer Vision (ICCV), 2015: 1026-1034.
    [8] [5] X. Chen, J. Weng, W. Lu, J. Xu. Deep Manifold Learning Combined with Convolutional Neural Networks for Action Recognition[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(09): 3938-3952.
    [9] [6] Z. Gao, T. Han, L. Zhu. Exploring the Cross-Domain Action Recognition Problem by Deep Feature Learning and Cross-Domain Learning[J]. IEEE Access, 2018,6(04): 68989-69008.
    [10] [7] Q. Cao, W. Zhang, Y. Zhu. Deep learning-based classification of the polar emotions of "moe"-style cartoon pictures[J]. Tsinghua Science and Technology, 2021, 26(03): 275-286.
    [11] [8] O. Russakovsky, et al. 2014 Imagenet large scale visual recognition challenge[J]. Int. J. Comput. Vis., 2014, 115(03): 211-252.
    [12] [9] D. Li, J. Huang, Y. Li. Progressive Representation Adaptation for Weakly Supervised Object Localization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(06): 1424-1438.
    [13] [10] K. He, X. Zhang, S. Ren, J. Sun. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification[C].2015 IEEE International Conference on Computer Vision (ICCV), 2015: 1026-1034.
    [14] [11] Z. Wang, S. Chang, Y. Yang, D. Liu. Studying Very Low Resolution Recognition Using Deep Networks[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 4792-4800.
    [15] [12] X. Peng, J. Hoffman, S. X. Yu. Fine-to-coarse knowledge transfer for low-res image classification[C]. 2016 IEEE International Conference on Image Processing (ICIP), 2016: 3683-3687.
    [16] [13] S. P. Mudunuri, S. Sanyal, S. Biswas. GenLR-Net: Deep Framework for Very Low Resolution Face and Object Recognition with Generalization to Unseen Categories[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018: 602-610.
    [17] [14] Cai D, Chen K, Qian Y, et al. Convolutional Low-Resolution Fine-Grained Classification[J]. Pattern Recognition Letters, 2019, 19(02): 119-125.
    [18] [15] Kim J, Lee J K, Lee K M. Accurate Image Super-Resolution Using Very Deep Convolutional Networks[C]. IEEE Conference on Computer Vision & Pattern Recognition, 2016: 345-352.
    [19] [16] Lim B, Son S, Kim H, et al. Enhanced Deep Residual Networks for Single Image Super-Resolution[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017: 987-994.
    [20] [17] M. S. M. Sajjadi, B. Scholkopf, M. Hirsch. EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis[C]. 2017 IEEE International Conference on Computer Vision (ICCV), 2017: 4501-4510.
    [21] [18] A. Mahendran, A. Vedaldi. Understanding deep image representations by inverting them[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 5188-5196.
    相似文献
    引证文献
    引证文献 [0] 您输入的地址无效!
    没有找到您想要的资源,您输入的路径无效!

    网友评论
    网友评论
    分享到微博
    发 布
引用本文
分享
文章指标
  • 点击次数:77
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2021-05-14
  • 最后修改日期:2021-08-11
  • 录用日期:2021-09-11
文章二维码