基于YOLO-tiny-RFB模型的电站旋钮开关状态识别

doi:10.11772/j.issn.1001-9081.2020071084

计算机应用 ›› 2020, Vol. 40 ›› Issue (12): 3679-3686.DOI: 10.11772/j.issn.1001-9081.2020071084

• 虚拟现实与多媒体计算 • 上一篇下一篇

基于YOLO-tiny-RFB模型的电站旋钮开关状态识别

史梦安¹, 陆振宇^2,3

1. 苏州大学应用技术学院, 江苏苏州 215325;
2. 南京信息工程大学人工智能学院, 南京 210044;
3. 江苏省大气环境与装备技术协同创新中心(南京信息工程大学), 南京 210044

收稿日期:2020-07-22 修回日期:2020-10-09 出版日期:2020-12-10 发布日期:2020-12-23
通讯作者: 史梦安(1985-),男,江苏淮安人,讲师,硕士,CCF会员,主要研究方向:机器学习、基于视觉的同步定位与地图构建方法。mashi@suda.edu.cn
作者简介:陆振宇(1976-),男,江苏常州人,教授,博士,主要研究方向:人工智能、智能控制、模式识别
基金资助:
江苏省高等学校自然科学研究项目（19KJB520051）；国家自然科学基金资助项目（61773220）。

Power station rotary switch status recognition based on YOLO-tiny-RFB model

SHI Meng'an¹, LU Zhenyu^2,3

1. Applied Technology College, Soochow University, Suzhou Jiangsu 215325, China;
2. School of Artificial Intelligence, Nanjing University of Information Science&Technology, Nanjing Jiangsu 210044, China;
3. Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(Nanjing University of Information Science&Technology), Nanjing Jiangsu 210044, China

Received:2020-07-22 Revised:2020-10-09 Online:2020-12-10 Published:2020-12-23
Supported by:
This work is partially supported by the Natural Science Research Foundation of Jiangsu Higher Education Institutions （19KJB520051）， the National Natural Science Foundation of China （61773220）.

摘要/Abstract

摘要： 针对多类别目标检测在特定场景中数据样本有限的情况，为进一步提高机器人系统中轻量级神经网络对小型物体识别的准确率和稳定性，提出了一种基于机器人操作系统（ROS）的目标状态识别模块。首先，考虑到嵌入式设备的算力限制，目标识别模型采用轻量级的网络YOLO-tiny作为主要架构，并在YOLO-tiny中引入RFB，提出了YOLO-tiny-RFB模型。随后，基于MobileNet对旋钮开关的多种状态实现精准分类。最后，设计数据关联规则，通过图像配准及交并比（IOU）计算等算法使识别模块完成同一场景多次识别结果的融合，从而使用户能够对不同时刻各表计的状态进行追踪。实验结果表明，相较于YOLO-tiny，YOLO-tiny-RFB模型在少量增加模型计算量的情况下，在构建的电站仪器识别数据集上，其目标识别平均精度均值（mAP）提升了17.9%，达到了82.4%。在旋钮数据分布极端不均衡的情况下，通过引入多种数据增广方法使模型的平均准确率达到了90.7%。所提出的目标检测模块和状态识别网络模型能够有效、准确地完成各类仪器的状态识别，同时能够对仪器状态的识别结果在时间跨度上进行融合。

关键词: 机器人操作系统, 目标检测, 图像分类, 轻量级神经网络, 数据增广, YOLO-tiny, RFB, 旋钮开关状态

Abstract: Data samples were always limited for multi-category object detection in some specific scenes. In order to improve the stability and accuracy of the light-weight neural networks for small object recognition in robotic system, an object status recognition module based on Robotic Operating System (ROS) was designed. Firstly, considering the computing power limitation of embedded devices, a lightweight network YOLO-tiny was used as the main architecture of object recognition model, then the Respective Field Block (RFB) was introduced in YOLO-tiny, so as to construct the YOLO-tiny-RFB model. Secondly, MobileNet was employed to conduct an accurate classification of multiple statuses of rotary switches. Finally, the data association rules were designed, and algorithms such as image alignment and Intersection Over Union (IOU) calculation were used to make the recognition module complete the fusion of multiple recognition results of the same scene, so that users were able to track the statuses of each meter at different times. Experimental results show that on the constructed power station instrument recognition dataset, compared with the YOLO-tiny, the YOLO-tiny-RFB model increases the object recognition mean Average Precision (mAP) by 17.9%, which is achieved to 82.4% with a small increase in computational load of model. In the case of extremely unbalanced rotary switch data distribution, the average accuracy of model reaches 90.7% by introducing various data enhancement methods. The proposed object detection module and status recognition network model can complete the status recognition of all kinds of instruments effectively and accurately, meanwhile they can fuse the recognition results of instrument status at different times.

Key words: Robotic Operating System (ROS), object detection, image classification, light-weight neural network, data argumentation, YOLO-tiny, Respective Field Block （RFB）, rotary switch status

中图分类号:

TP391.4

史梦安, 陆振宇. 基于YOLO-tiny-RFB模型的电站旋钮开关状态识别[J]. 计算机应用, 2020, 40(12): 3679-3686.

SHI Meng'an, LU Zhenyu. Power station rotary switch status recognition based on YOLO-tiny-RFB model[J]. Journal of Computer Applications, 2020, 40(12): 3679-3686.

参考文献

[1] SIMONYAN K,ZISSERMAN A. Very deep convolutionalnetworks for large-scale image recognition[EB/OL].[2019-04-10]. https://arxiv.org/pdf/1409.1556.pdf.
[2] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778.
[3] REDMON J,DIVVALA S,GIRSHICK R,et al. You only look once:unified,real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2016:779-788.
[4] REDMON J,FARHADI A. YOLO9000:better,faster,stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:6517-6525.
[5] REDMON J,FARHADI A. YOLOv3:an incremental improvement[EB/OL].[2020-06-08]. https://arxiv.org/pdf/1804.02767.pdf.
[6] HOWARD A G,ZHU M,CHEN B,et al. MobileNets:efficient convolutional neuralnetworks for mobile vision applications[EB/OL].[2020-06-08]. https://arxiv.org/pdf/1704.04861.pdf.
[7] SANDLER M, HOWARD A, ZHU M, et al. MobileNetV2:inverted residuals and linear bottlenecks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:4510-4520.
[8] ZHANG X,ZHOU X,LIN M,et al. ShuffleNet:an extremely efficient convolutional neuralnetwork for mobile devices[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:6848-6856.
[9] LIU S,HUANG D,WANG Y. Receptive field blocknet for accurate and fast object detection[C]//Proceedings of the 2018 European Conference on Computer Vision,LNCS 11215. Cham:Springer,2018:404-419.
[10] 朱繁, 王洪元, 张继. 基于改进的Mask R-CNN的行人细粒度检测算法[J]. 计算机应用, 2019, 39(11):3210-3215.(ZHU F, WANG H Y, ZHANG J. Fine-grained pedestrian detection algorithm based on improved mask R-CNN[J]. Journal of Computer Applications,2019,39(11):3210-3215.)
[11] 张家晨, 陈庆奎. 基于YOLO的道路车辆拥堵分析模型[J]. 计算机应用, 2019, 39(1):93-97.(ZHANG J C,CHEN Q K. Road vehicle congestion analysis model based on YOLO[J]. Journal of Computer Applications,2019,39(1):93-97.)
[12] 聂鑫, 刘文, 吴巍. 复杂场景下基于增强YOLOv3的船舶目标检测[J]. 计算机应用, 2020, 40(9):2561-2570.(NIE X,LIU W, WU W. Ship detection based on enhanced YOLOv3 undercomplex environments[J]. Journal of Computer Applications, 2020,40(9):2561-2570.)
[13] GIRSHICK R,DONAHUE J,DARRELL T,et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2014:580-587.
[14] UIJLINGS J R R,VAN DE SANDE K E A,GEVERS T,et al. Selective search for object recognition[J]. International Journal of Computer Vision,2013,104(2):154-171.
[15] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2015:1440-1448.
[16] REN S,HE K,GIRSHICK R,et al. Faster R-CNN:towards realtime object detection with region proposalnetworks[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence,2017, 39(6):1137-1149.
[17] LIU W,ANGUELOV D,ERHAN D,et al. SSD:Single Shot MultiBox Detector[C]//Proceedings of the 2016 European Conference on Computer Vision,LNCS 9905. Cham:Springer, 2016:21-37.
[18] RONNEBERGER O, FISCHER P, BROX T. U-net:convolutionalnetworks for biomedical image segmentation[C]//Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham:Springer,2015:234-241.
[19] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2015:1-9.
[20] CHEN L C,PAPANDREOU G,KOKKINOS I,et al. DeepLab:Semantic image segmentation with deep convolutionalnets,atrous convolution,and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4):834-848.
[21] ZHUANG F,QI Z,DUAN K,et al. Acomprehensive survey on transfer learning[EB/OL].[2020-07-05]. https://arxiv.org/pdf/1911.02685.pdf.
[22] HU J,SHEN L,SUN G. Squeeze-and-excitationnetworks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:7132-7141.
[23] SHORTEN C,KHOSHGOFTAAR T M. A survey on image data augmentation for deep learning[J]. Journal of Big Data,2019, 6:Article No. 60.

基于YOLO-tiny-RFB模型的电站旋钮开关状态识别

Power station rotary switch status recognition based on YOLO-tiny-RFB model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[2]	马佳良, 陈斌, 孙晓飞. 基于改进的Faster R-CNN的通用目标检测框架[J]. 计算机应用, 2021, 41(9): 2712-2719.
[3]	樊玮, 李晨炫, 邢艳, 黄睿, 彭洪健. 航空发动机损伤图像的二分类到多分类递进式检测网络[J]. 计算机应用, 2021, 41(8): 2352-2357.
[4]	陈静, 毛莺池, 陈豪, 王龙宝, 王子成. 基于改进单点多盒检测器的大坝缺陷目标检测方法[J]. 计算机应用, 2021, 41(8): 2366-2372.
[5]	肖振远, 王逸涵, 罗建桥, 熊鹰, 李柏林. 基于部分加权损失函数的RefineDet[J]. 计算机应用, 2021, 41(7): 1928-1932.
[6]	李朝, 兰海, 魏宪. 基于注意力的毫米波-激光雷达融合目标检测[J]. 计算机应用, 2021, 41(7): 2137-2144.
[7]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[8]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.
[9]	贾鹤鸣, 郎春博, 姜子超. 基于轻量级卷积神经网络的植物叶片病害识别方法[J]. 计算机应用, 2021, 41(6): 1812-1819.
[10]	胡嵽, 冯子亮. 基于深度学习的轻量级道路图像语义分割算法[J]. 计算机应用, 2021, 41(5): 1326-1331.
[11]	后云龙, 朱磊, 陈琴, 吕燧栋. 基于高斯差分特征网络的显著目标检测[J]. 计算机应用, 2021, 41(3): 706-713.
[12]	曹建荣, 吕俊杰, 武欣莹, 张旭, 杨红娟. 融合运动特征和深度学习的跌倒检测算法[J]. 计算机应用, 2021, 41(2): 583-589.
[13]	蒋宁, 方景龙, 杨庆. 基于单点多盒检测器的全局-局部层级的域适应目标检测[J]. 计算机应用, 2021, 41(2): 517-522.
[14]	郑思诚, 孔令华, 游通飞, 易定容. 动态环境下基于深度学习的语义SLAM算法[J]. 计算机应用, 2021, 41(10): 2945-2951.
[15]	裴仪瑶, 郭会明, 张丹普, 陈文博. 基于定位不确定性的鲁棒3D目标检测方法[J]. 计算机应用, 2021, 41(10): 2979-2984.