|本期目录/Table of Contents|

[1]康朝海,刘 杨,任伟建,等.基于Mask R-CNN的油田井场指针仪表识别方法研究[J].工业仪表与自动化装置,2024,(05):76-82.[doi:DOI:10.19950/j.cnki.cn61-1121/th.2024.05.015]
 KANG Chaohai,LIU Yang,REN Weijian,et al.Research on Mask R-CNN-based pointer instrument recognition method for oilfield wellsite[J].Industrial Instrumentation & Automation,2024,(05):76-82.[doi:DOI:10.19950/j.cnki.cn61-1121/th.2024.05.015]
点击复制

基于Mask R-CNN的油田井场指针仪表识别方法研究(PDF)

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2024年05期
页码:
76-82
栏目:
出版日期:
2024-10-15

文章信息/Info

Title:
Research on Mask R-CNN-based pointer instrument recognition method for oilfield wellsite
文章编号:
1000-0682(2024)05-0076-07
作者:
康朝海刘 杨任伟建
( 1.东北石油大学 电气信息工程学院,黑龙江 大庆 163318;2.大庆油田有限责任公司第二采油厂,黑龙江 大庆 163414)
Author(s):
KANG Chaohai LIU Yang REN Weijian et al
( 1. Northeast Petroleum University Daqing,Heilongjiang Daqing 163318, China;2.Second Oil Production Plant ofDaqing Oilfield Co.,Ltd.,Heilongjiang Daqing 163414, China )
关键词:
计算机视觉Mask RCNNMobileNetV3仪表识别图像去模糊
Keywords:
computer visionMask RCNNMobileNetV3instrument identificationimage deblurring
分类号:
TP391
DOI:
DOI:10.19950/j.cnki.cn61-1121/th.2024.05.015
文献标志码:
A
摘要:
针对无人机巡检流程中采集到井场仪表图像模糊以及油田仪表定位模型实时性较差的问题,提出一种改进后最大后验概率模型去模糊方法和基于 Mask R -CNN 的指针式仪表定位算法。首先,通过采用变步长 LMS 滤波器的方法优化图像的先验信息,根据输入数据的统计特性调整滤波器参数,生成初步的仪表图像恢复结果,从而提升了最大后验概率的去模糊效果;其次,在Mask R -CNN 网络结构的基础上,选用 MobileNetV3 作为主干特征提取网络减少参数量,再加入注意力机制模块保证准确率以完成仪表定位。 最后,实验证明,仪表图像评价指标高于其他算法,该文提出的仪表定位算法减少了 48.25 M 参数量,FPS 值达到 37.3 frame/s,准确率为 94.02% 。
Abstract:
Aiming at the problems of fuzzy wellsite instrumentation images captured during the UAV inspection process and the poor real-time oilfield instrumentation localization model, an improved maximum a posteriori probability model deblurring method and a pointer instrumentation localization algorithm based on Mask R-CNN are proposed. Firstly, the a priori information of the image is optimized by using a variable step size LMS filter, and the filter parameters are adjusted according to the statistical characteristics of the input data to generate preliminary instrument image recovery results, so as to improve the deblurring effect of the maximum a posteriori probability. Secondly, based on the Mask R-CNN network structure, MobileNetV3 is selected as the main feature extraction network to reduce the number of parameters, and the attention mechanism module is added to ensure the accuracy of the Mask R-CNN network structure to complete the instrument positioning. Finally, the experiment proves that the evaluation index of the instrument image is higher than other algorithms. The instrument localization algorithm proposed in this paper reduces the number of parameters by 48.25M, and the FPS value reaches 37.3 frames/s, with an accuracy rate of 94.02%.

参考文献/References:

[1] 熊国良,肖文明,王小明. 基于视觉的指针式仪表检测与识别方法综述 [J]. 传感器与微系统,2020,39(12):1-3+9.

[2] LIU Y, LIU J, KEY. A detection and recognition system of pointer meters in substations based on computer vision [J]. Measurement, 2020(152):107333.
[3] WU X, SHI X, JIANG Y, et al. A high-precision automatic pointer meter reading system in low-light environment [J]. Sensors, 2021,21(14):4891.
[4] 陈梦迟,黄文君,张阳阳,等. 基于机器视觉的工业仪表识别技术研究 [J]. 控制工程,2020,27(11):1995-2001.
[5] 刘晏,李玉梅,张涛,等. 基于改进的YOLOv5s指针式仪表检测与读数识别 [J]. 北京信息科技大学学报(自然科学版),2023,38(03):9-14.
[6] 刘海龙,马波,张奇志. 钻井现场指针式仪表读数自动识别方法研究 [J/OL]. 控制工程,2023,30(09):1665-1672.
[7] 贺嘉琪. 基于深度学习的指针式仪表示数自动识别的研究与应用 [D]. 北京:北京邮电大学,2019.
[8] HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3 [C]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
[9] HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design [C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[10] 张文政,吴长悦,赵文,等. 融合对抗网络和维纳滤波的无人机图像去模糊方法研究 [J]. 无线电工程,2024,54(03):607-614.
[11] PAN J, HU Z, SU Z, et al. Deblurring text images via L0-regularized intensity and gradient prior [C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 2014:2901-2908. https://doi.org/10.1109/CVPR.2014.371.
[12] 佟雨兵,张其善,祁云平. 基于PSNR与SSIM联合的图像质量评价模型 [J]. 中国图象图形学报,2006(12):1758-1763.

相似文献/References:

[1]阎 翔,谌海云,蒋 钰,等.基于计算机视觉的车道线检测与识别[J].工业仪表与自动化装置,2020,(01):118.
 YAN Xiang,SHEN Haiyun,JIANG Yu,et al.Lane line detection and recognition based on computer vision[J].Industrial Instrumentation & Automation,2020,(05):118.

备注/Memo

备注/Memo:
收稿日期:2024-04-08第一作者:康朝海(1976 — ),男,蒙古族,副教授,硕士,研究方向为模式识别与智能系统。E -mail:kangchaohai@ 126.com
更新日期/Last Update: 1900-01-01