基于改进YOLOX算法的给水管道内缺陷智能识别与定位

doi:10.13474/j.cnki.11-2246.2023.0361

测绘通报 ›› 2023, Vol. 0 ›› Issue (12): 70-75.doi: 10.13474/j.cnki.11-2246.2023.0361

基于改进YOLOX算法的给水管道内缺陷智能识别与定位

苏常旺¹, 胡少伟², 张海丰³, 潘福渠⁴, 单常喜¹

1. 重庆大学土木工程学院, 重庆 400045;
2. 郑州大学水利与土木工程学院, 河南郑州 450001;
3. 山东龙泉管道工程股份有限公司, 江苏常州 277599;
4. 山东东信塑胶科技有限公司, 山东聊城 252000

收稿日期:2023-03-13 出版日期:2023-12-25 发布日期:2024-01-08
通讯作者: 胡少伟。E-mail:hushaowei@zzu.edu.cn
作者简介:苏常旺(1996-),男,博士生,主要研究方向为管道智能监测与检测。E-mail:1533661722@qq.com
基金资助:
重庆市自然科学基金创新群体科学基金(cstc2020jcyj-cxttX0003);国家自然科学基金重点项目(52130901;51739008);重庆市技术创新与应用发展专项重点项目(cstc2019jscx-gksbX0013);泰山产业领军人才工程专项经费

Intelligent identification and location of defects in water supply pipeline based on improved YOLOX algorithm

SU Changwang¹, HU Shaowei², ZHANG Haifeng³, PAN Fuqu⁴, SHAN Changxi¹

1. School of Civil Engineering, Chongqing University, Chongqing 400045, China;
2. College of Water Resources and Civil Engineering, Zhengzhou University, Zhengzhou 450001, China;
3. Shandong Longquan Pipeline Engineering Co., Ltd., Changzhou 277599, China;
4. Shandong Dongxin Plastic Technology Co., Ltd., Liaocheng 252000, China

Received:2023-03-13 Online:2023-12-25 Published:2024-01-08

摘要/Abstract

摘要： 针对给水管道内缺陷难以快速实时自动化检测的问题,本文基于实际工程项目中采集到的管道缺陷数据集,通过增加注意力模块,得到改进后的新型YOLOX算法模型,从而提出了一种给水管道智能识别与定位方法。利用视频抽帧的方式制作数据集并进行算法模型的训练与预测。测试结果表明:①基于注意力机制的YOLOX算法模型可以达到平均94%的测试精度,均值平均精度达到84%,平均识别速度为16 m/s;②新模型与其他2种常用算法模型(YOLOV3和Fast R-CNN)的训练结果进行对比,其综合性能最好。本文所提出的算法模型同样可以应用于视频实时检测,为给水管道内缺陷智能识别定位提供了一种高效精确的检测技术和方法。

关键词: 给水管道缺陷, 改进YOLOX算法, 注意力机制, 识别与定位

Abstract: To solve the problem of difficult and slow real-time automated detection of defects in water supply pipelines, a new intelligent identification and positioning method for water supply pipelines is proposed based on a dataset of pipeline defect data collected from actual engineering projects. The new YOLOX algorithm model, which incorporates an attention module, is developed and used for algorithm training and prediction using a dataset of video frames. Test results show that the YOLOX algorithm model with attention mechanism achieved an average testing accuracy of 94%, a mAP value of 84%, and an average recognition speed of 16 m/s. Additionally, compared with three other commonly used algorithm models (YOLO V3 and Fast R-CNN), the new model showed the best overall performance. This proposed model can also be applied to real-time video detection, providing an efficient and accurate detection technology and method for the intelligent identification and positioning of defects in water supply pipelines.

Key words: defects in water supply pipeline, improved YOLOX algorithm, attention mechanism, identification and localization

中图分类号:

P258

苏常旺, 胡少伟, 张海丰, 潘福渠, 单常喜. 基于改进YOLOX算法的给水管道内缺陷智能识别与定位[J]. 测绘通报, 2023, 0(12): 70-75.

SU Changwang, HU Shaowei, ZHANG Haifeng, PAN Fuqu, SHAN Changxi. Intelligent identification and location of defects in water supply pipeline based on improved YOLOX algorithm[J]. Bulletin of Surveying and Mapping, 2023, 0(12): 70-75.

参考文献

[1] 李海燕,徐尚玲,黄延,等. 合流制排水管道雨季出流污染负荷研究[J]. 环境科学学报,2013,33(9): 2522-2530.
[2] KUMAR S S,WANG M,ABRAHAM D M,et al. Deep learning-based automated detection of sewer defects in CCTV videos[J]. Journal of Computing in Civil Engineering,2020,34(1): 1-13.
[3] HAWARI A,ALAMIN M,ALKADOUR F,et al. Automated defect detection tool for closed circuit television (CCTV) inspected sewer pipelines[J]. Automation in Construction,2018,89:99-109.
[4] GU Jiuxiang,WANG Zhenhua,KUEN J,et al. Recent advances in convolutional neural networks[EB/OL]. 2015-12-01[2023-02-20].https://arxiv.org/abs/1512.07108.
[5] WANG M,CHENG J C P. A unified convolutional neural network integrated with conditional random field for pipe defect segmentation[J]. Computer-Aided Civil and Infrastructure Engineering,2020,35(2):162-177.
[6] MORRIS A C. Robotic introspection for exploration and mapping of subterranean environments[D]. Pittsburgh: Carnegie Mellon University,2007.
[7] DURAN,O,ALTHOEFER K,SENEVIRATNE L D.Pipe inspection using a laser-based transducer and automated analysis techniques[J].IEEE/ASME Transactions on Mechatronics,2003,8(3):401-409.
[8] 吕兵,刘玉贤,叶绍泽,等. 基于卷积神经网的CCTV视频中排水管道缺陷的智能检测[J]. 测绘通报,2019(11): 103-108.
[9] REN S,HE K,GIRSHICK R,et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6): 1137-1149.
[10] GE Zheng,LIU Songtao,WANG Feng,et al. YOLOX: exceeding YOLO series in 2021[EB/OL]. 2021-06-18[2023-03-01].https://arxiv.org/abs/2107.08430.
[11] 代科学,李国辉,涂丹,等. 监控视频运动目标检测减背景技术的研究现状和展望[J]. 中国图象图形学报,2006,11(7): 919-927.
[12] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once: unified,real-time object detection[EB/OL].2015-07-08[2023-01-11]. https://doi.org/10.48550/arXiv.1506.02640.
[13] REDMON J,FARHADI A. YOLOv3: an incremental improvement[EB/OL]. 2018-04-08[2023-01-11]. https://arxiv.org/abs/1804.02767.
[14] LIN T Y,DOLLAR P,GIRSHICK R,et al. Feature pyramid networks for object detection[C]// Processings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu:IEEE,2017.
[15] VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.[S.l.]:ACM Press,2017.

基于改进YOLOX算法的给水管道内缺陷智能识别与定位

Intelligent identification and location of defects in water supply pipeline based on improved YOLOX algorithm

RichHTML

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

本文评价

[1]	杜宇峰, 黄亮, 赵子龙, 李国柱. 基于DETR的高分辨率遥感影像滑坡体识别与检测[J]. 测绘通报, 2023, 0(5): 16-20.
[2]	雷洋洋, 李礼, 孙飞, 姚剑. 一种基于域适应的动态商品视觉识别方法[J]. 测绘通报, 2023, 0(3): 10-15.
[3]	吴瑞姣. 混合U-Net模型下南方丘陵地区耕地识别[J]. 测绘通报, 2023, 0(12): 57-62,111.
[4]	李朋朋, 刘纪平, 王勇, 罗安, 桑瑜, 闫雪峰. 顾及地址语义和地理空间特征的多源POI位置融合[J]. 测绘通报, 2023, 0(11): 54-60.
[5]	胡春霞, 聂翔宇, 林聪, 傅俊豪, 储征伟. 利用多特征协同深度网络的高分遥感影像分类[J]. 测绘通报, 2023, 0(10): 74-79,104.
[6]	宋伟东, 毕春杨, 赵奉书. 改进Mask R-CNN公路病害检测算法[J]. 测绘通报, 2023, 0(1): 58-64.
[7]	唐菲菲, 唐天俊, 朱洪洲, 胡川, 马英, 李昕. 结合注意力机制和Bi-LSTM的降雨型滑坡位移预测[J]. 测绘通报, 2022, 0(9): 74-79,104.
[8]	潘建平, 李鑫, 孙博文, 胡勇, 李明明. 基于注意力密集连接金字塔网络的新增建设用地变化检测[J]. 测绘通报, 2022, 0(3): 41-46,59.
[9]	杨勇, 崔丽珍, 郭倩倩, 薛中浩. 煤矿井下基于Attention机制的LSTM地磁定位算法[J]. 测绘通报, 2022, 0(1): 72-78.
[10]	吴永静, 吴锦超, 林超, 窦宝成, 黎珂. 基于深度学习的高分辨率遥感影像光伏用地提取[J]. 测绘通报, 2021, 0(5): 96-101.
[11]	刘广进, 王光辉, 毕卫华, 刘慧杰, 杨化超. 改进D-LinkNet模型在国产卫星影像云检测中的应用[J]. 测绘通报, 2021, 0(11): 54-58,64.
[12]	马林飞, 倪欢, 周子涵. 基于注意力机制的高分遥感图像采石场识别[J]. 测绘通报, 2021, 0(11): 96-100.
[13]	胡建朗, 罗亚荣, 郭迟. 一种用于运动姿态评估的视觉伺服机器人[J]. 测绘通报, 2020, 0(8): 33-38.
[14]	张朕通, 单玉刚, 袁杰. 改进注意力机制的遥感地貌识别算法[J]. 测绘通报, 2020, 0(10): 93-96,100.
[15]	西秀秀, 孙久运, 汪云甲, 张新耐, 刘克强. 一种改进条码尺编码的闸门开度测量方法[J]. 测绘通报, 2018, 0(1): 92-96.