面向设备开关图像识别的改进Faster R-CNN
作者:
基金项目:

国网新源控股有限公司科技项目(SGXY2000074)


Improved Faster R-CNN for Recognition of Device Switch Images
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [33]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    在大型工业厂房中, 由于设备控制开关种类繁多、数量庞大, 在日常的运维过程中, 操作规程的繁杂性和人为判断的主观性可能导致操作失误, 造成严重后果. 为辅助操作人员准确判断设备开关状态是否正确, 提出了面向设备开关状态识别的改进Faster R-CNN. 首先, 使用膨胀残差网络作为特征提取网络, 在ResNet50中引入多分支膨胀卷积, 融合不同感受野的信息; 其次, 改进特征金字塔网络, 在原网络上增加一条自底向上的特征增强分支, 融合多尺度的特征信息; 然后, 使用K-means++算法对开关边界框聚类, 设计适合设备开关的候选框尺寸; 最后, 使用Soft-NMS代替非极大值抑制算法NMS来降低开关重叠对检测效果的影响, 增强抑制重叠候选框的能力. 在开关状态数据集上, 改进Faster R-CNN的均值平均精度(mAP)达到了91.5%, 并且已实际应用于抽水蓄能电站日常运维的设备开关状态辅助识别, 满足复杂场景下的智能监管需求.

    Abstract:

    In large industrial plants, due to a wide variety and a large number of equipment control switches, the complexity of operating procedures and the subjectivity of human judgment may lead to operational errors and cause serious consequences in the daily operation and maintenance process. To assist operators in accurately judging whether the state of an equipment switch is correct, an improved Faster R-CNN algorithm is proposed for state recognition of equipment switches. Firstly, the dilated residual network (ResNet) is used as the feature extraction network, and the multi-branch dilated convolution is introduced into ResNet50 to fuse the information of different receptive fields. Secondly, the feature pyramid network is improved by the addition of a bottom-up feature enhancement branch to the original network, which is used to integrate multi-scale feature information. Then, the K-means++ algorithm is applied to cluster bounding boxes of switches, and the size of proposals for equipment switches is designed. Finally, the non-maximum suppression (NMS) algorithm is replaced with Soft-NMS to reduce the influence of switch overlap on the detection effect and enhance the performance of suppressing the overlapping proposals. On a switch state dataset, the mean average precision (mAP) of the improved Faster R-CNN reaches 91.5%. Moreover, it has been applied to assist state recognition of equipment switches in the daily operation and maintenance of pumped-storage power stations to meet the needs of intelligent supervision in complex scenarios.

    参考文献
    [1] 彭小圣, 邓迪元, 程时杰, 等. 面向智能电网应用的电力大数据关键技术. 中国电机工程学报, 2015, 35(3): 503–511
    [2] Li B, Li T, Xu NW, et al. Stability assessment of the left bank slope of the Baihetan Hydropower Station, Southwest China. International Journal of Rock Mechanics and Mining Sciences, 2018, 104: 34–44. [doi: 10.1016/j.ijrmms.2018.02.016
    [3] Zhu YM, Chen SJ, Ma GW, et al. Complementary operation of a small cascade hydropower station group and photovoltaic power stations. Clean Technologies and Environmental Policy, 2020, 22(7): 1565–1578. [doi: 10.1007/s10098-020-01896-x
    [4] 周凯, 唐瞾, 胡志坚, 等. 基于NSST图像融合的变电站开关状态识别. 高压电器, 2021, 57(10): 50–58
    [5] 孟令枫, 杨兴, 于晓春, 等. 基于直线检测法的变电站开关状态图像识别系统的研究. 电子质量, 2017, (4): 5–8. [doi: 10.3969/j.issn.1003-0107.2017.04.002
    [6] 胡聪, 施保华, 王俊. 智能变电站隔离开关状态图像识别新方法. 电力学报, 2019, 34(5): 498–504
    [7] 汪洋, 黎恒烜, 鄂士平, 等. 基于深度学习的变电站硬压板状态检测与识别算法. 沈阳工业大学学报2020, 42(6): 676–680.
    [8] 周克, 杨倩文, 王耀艺, 等. 一种改进的压板状态识别SSD算法. 电测与仪表, 2021, 58(1): 69–76
    [9] 许根养, 翁士状, 孙长翔, 等. 基于相位特征的保护压板状态的准确识别方法. 安徽大学学报(自然科学版), 2020, 44(3): 38–42
    [10] 阮浩洁, 王春亚, 王辉, 等. 基于图像识别的保护压板状态识别技术研究与应用. 电力设备管理, 2020, (1): 139–140
    [11] 黄钊鹏. 变电站保护压板中开关的图像识别方法研究[硕士学位论文]. 武汉: 武汉理工大学, 2019.
    [12] 冷从林. 基于机器视觉的变电站压板开关状态识别系统研究[硕士学位论文]. 武汉: 武汉理工大学, 2019.
    [13] 李瑮. 基于图像识别的电力智能巡检系统设计与实现[硕士学位论文]. 南京: 南京大学, 2018.
    [14] 史梦安, 陆振宇. 基于YOLO-tiny-RFB模型的电站旋钮开关状态识别. 计算机应用, 2020, 40(12): 3679–3686
    [15] 杨雨, 陈服, 陈柏青, 等. 基于深度学习的变电站保护硬压板检测与状态识别技术研究. 科技创新与应用, 2021, 11(24): 25–29
    [16] 李岩, 李丹, 李建, 等. 基于机器视觉的电力设备监测系统的研究. 中小企业管理与科技, 2021, (11): 194–196
    [17] 苏杨, 余萱. 基于卷积神经网络的机房柜门开关状态识别研究. 工业仪表与自动化装置, 2019, (5): 22–25, 47. [doi: 10.3969/j.issn.1000-0682.2019.05.005
    [18] 邓乐武, 成金涛, 曾苏凡. 基于深度学习的座舱开关状态识别研究. 测控技术, 2021, 40(8): 54–57
    [19] 高露. 基于深度学习的变电站开关状态识别系统的设计与实现[硕士学位论文]. 沈阳: 中国科学院大学, 2019.
    [20] Khan D. 基于深度学习的电力开关检测与状态识别[硕士学位论文]. 成都: 电子科技大学, 2018.
    [21] 张礼波, 雷鸣, 周怡君. 基于目标跟踪的变电站隔离开关状态图像识别方法. 机械与电子, 2020, 38(1): 36–39. [doi: 10.3969/j.issn.1001-2257.2020.01.009
    [22] Ren SQ, He KM, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137–1149. [doi: 10.1109/TPAMI.2016.2577031
    [23] Lin TY, Dollár P, Girshick R, et al. Feature pyramid networks for object detection. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017. 936–944.
    [24] Redmon J, Farhadi A. YOLOv3: An incremental improvement. arXiv: 1804.02767, 2018.
    [25] Liu W, Anguelov D, Erhan D, et al. SSD: Single shot MultiBox detector. Proceedings of the 14th European Conference on Computer Vision. Amsterdam: Springer, 2016. 21–37.
    [26] Arthur D, Vassilvitskii S. K-means++: The advantages of careful seeding. Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms. New Orleans Louisiana: Society for Industrial and Applied Mathematics, 2007. 1027–1035.
    [27] He KM, Zhang XY, Ren SQ, et al. Deep residual learning for image recognition. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016. 770–778.
    [28] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556, 2014.
    [29] Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. arXiv: 1511.07122, 2015.
    [30] Li YH, Chen YT, Wang NY, et al. Scale-aware trident networks for object detection. Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019. 6053–6062.
    [31] Liu ST, Huang D, Wang YH. Receptive field block net for accurate and fast object detection. Proceedings of the 15th European Conference on Computer Vision. Munich: Springer, 2018. 404–419.
    [32] Yang X, Sun H, Fu K, et al. Automatic ship detection in remote sensing images from Google Earth of complex scenes based on multiscale rotation dense feature pyramid networks. Remote Sensing, 2018, 10(1): 132. [doi: 10.3390/rs10010132
    [33] Bodla N, Singh B, Chellappa R, et al. Soft-NMS-improving object detection with one line of code. Proceedings of 2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017. 5562–5570.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

宋旭峰,蒋梦姣,周怡伶,吉俊杰,陆晓翔.面向设备开关图像识别的改进Faster R-CNN.计算机系统应用,2022,31(10):211-224

复制
分享
文章指标
  • 点击次数:747
  • 下载次数: 1607
  • HTML阅读次数: 1670
  • 引用次数: 0
历史
  • 收稿日期:2021-12-10
  • 最后修改日期:2022-01-10
  • 在线发布日期: 2022-07-07
文章二维码
您是第11208051位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号