基于改进YOLO模型的中缅油气管道遥感图像高后果区识别方法

doi:10.16265/j.cnki.issn1003-3033.2025.01.0632

中国安全科学学报 ›› 2025, Vol. 35 ›› Issue (1): 103-111.doi: 10.16265/j.cnki.issn1003-3033.2025.01.0632

基于改进YOLO模型的中缅油气管道遥感图像高后果区识别方法

姜垣良¹^,²^,³(), 任庆滢³^,⁴, 任远², 刘海鹏¹^,²^,³, 董绍华¹^,³^,^**()

¹ 中国石油大学(北京) 安全与海洋工程学院,北京 102249
² 中国石油集团中油国际管道公司, 北京 102206
³ 中国石油大学(北京) 油气生产安全与应急技术应急管理部重点实验室, 北京 102249
⁴ 中国石油大学(北京) 人工智能学院,北京 102249

收稿日期:2024-08-16 修回日期:2024-10-21 出版日期:2025-01-28
通信作者:
**董绍华(1972—),男,山东寿光人,博士,二级教授,博士生导师,主要从事安全工程、管道完整性管理技术、管道运行维护技术、管道安全评价技术、管道信息工程技术等方面的研究。E-mail:shdong@cup.edu.cn。
作者简介:
姜垣良 (1986—),男,吉林松原人,博士研究生,高级工程师,主要从事资源与环境、管道运输安全等方面的研究。E-mail:yuanliang.jiang@cnpc.com.cn。
任远高级工程师
刘海鹏高级工程师
董绍华教授
基金资助:
中国石油天然气集团有限公司-中国石油大学(北京)战略合作科技专项(ZLZX2020-05)

High-consequence area indentation of remote sensing images of China-Myanmar oil and gas pipeline based on improved YOLO model

JIANG Yuanliang¹^,²^,³(), REN Qingying³^,⁴, REN Yuan², LIU Haipeng¹^,²^,³, DONG Shaohua¹^,³^,^**()

¹ College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China
² CNPC International Pipeline Company, Beijing 102206, China
³ Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, China University of Petroleum (Beijing), Beijing 102249, China
⁴ College of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102249, China

Received:2024-08-16 Revised:2024-10-21 Published:2025-01-28

摘要/Abstract

摘要：

为解决中缅油气管道国外段外界环境敏感且复杂多变、人工巡检难度大、危险系数高的问题,提出一种改进的高后果区目标检测算法。首先通过引入卷积注意力模块(CBAM)自适应地学习通道和空间注意力,以增强网络的感知能力和泛化能力;然后使用精确边界框回归的高效交并比(Focal-EIoU)损失全面考虑目标特征和相互关系,处理类别不平衡问题,减少易分类样本的干扰,增强模型鲁棒性;最后将改进模型应用至中缅油气管线遥感图像地区属性化智能识别,并进行相关消融试验,以验证改进YOLO模型的有效性。结果表明: 采用所提方法识别中缅油气管线遥感图像特征,田地、绿地、居住地、河流4类地区检测的平均精度均值(mAP)达68.2%;相比于YOLOv5、YOLOx及YOLOv8分别提高29%、21.6%、10.7%。

关键词: YOLO, 中缅油气管道, 遥感图像, 高后果区, 目标检测, 智能识别

Abstract:

An improved object detection algorithm for high-consequence areas was proposed to solve the problems of the sensitive and complex external environment of the overseas section of the China-Myanmar oil and gas pipeline, difficulty in manual inspection, and high-risk factors. Firstly, a convolutional block attention module was used to adaptively learn channel and spatial attention to enhance the network's perception and generalization capabilities. Then, focal and efficient intersection over union(Focal-EIoU) loss was used to comprehensively consider the target features and their associations to deal with the issues of class imbalance, reduce the interference of easy-to-classify samples, and enhance the robustness of the model. Finally, the improved model was used to intelligently recognize regional attributes of China-Myanmar oil and gas pipeline remote sensing images. Furthermore, the proposed YOLO model was validated against related ablation experiments. The results showed that for the feature recognition of remote sensing images of the China-Myanmar oil and gas pipeline, the proposed model reached a mean average precision (mAP) of 68.2% for the field, green space, settlement, and river. The model performance was improved by 29%, 21.6%, and 10.7% compared with YOLOv5, YOLOx, and YOLOv8, respectively.

Key words: YOLO, China-Myanmar oil and gas pipeline, remote sensing images, high consequence areas, object detection, intelligent identification

中图分类号:

X924.2安全监测技术与设备

姜垣良, 任庆滢, 任远, 刘海鹏, 董绍华. 基于改进YOLO模型的中缅油气管道遥感图像高后果区识别方法[J]. 中国安全科学学报, 2025, 35(1): 103-111.

JIANG Yuanliang, REN Qingying, REN Yuan, LIU Haipeng, DONG Shaohua. High-consequence area indentation of remote sensing images of China-Myanmar oil and gas pipeline based on improved YOLO model[J]. China Safety Science Journal, 2025, 35(1): 103-111.

图/表 17

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

图10

图11

图12

图13

表2

图14

图15

参考文献 24

[1]	王晓霖, 帅健, 宋红波, 等. 输油管道高后果区识别与分级管理[J]. 中国安全科学学报, 2015, 25(6): 149-154.
	WANG Xiaolin, SHUAI Jian, SONG Hongbo, et al. Identification and hierarchical management of high consequence areas for oil pipeline[J]. China Safety Science Journal, 2015, 25(6): 149-154.
[2]	刘天颖, 李文根, 关佶红. 基于深度学习的光学遥感图像目标检测方法综述[J]. 无线电通信技术, 2020, 46(6): 624-634.
	LIU Tianying, LI Wengen, GUAN Jihong. Deep learning based object detection in optical remote sensing images: a survey[J]. Radio Communications Technology, 2020, 46(6): 624-634.
[3]	冯长峰, 王春平, 付强, 等. 基于深度学习的光学遥感图像目标检测综述[J]. 激光与红外, 2023, 53(9): 1309-1319.
	FENG Changfeng, WANG Chunping, FU Qiang, et al. Survey of object detection in optical remote sensing images based on deep learning[J]. Laser & Infrared, 2023, 53(9): 1309-1319.
[4]	KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25(2):DOI:10.1145/3065386.
[5]	YANG Yiding, ZHUANG Yin, BI Fukun, et al. M-FCN: effective fully convolutional network-based airplane detection framework[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(8): 1293-1297.
[6]	CHEN Zhong, ZHANG Ting, OUYANG Chao. End-to-end airplane detection using transfer learning in remote sensing images[J]. Remote Sensing, 2018, 10(1): DOI:10.3390/rs10010139.
[7]	LIN Haoning, SHI Zhenwei, ZOU Zhengxia. Fully convolutional network with task partitioning for inshore ship detection in optical remote sensing images[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(10): 1665-1669.
[8]	KANG Miao, LENG Xiangguang, LIN Zhao, et al. A modified faster R-CNN based on CFAR algorithm for SAR ship detection[C]. Proceedings of the 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP), 2017: DOI:10.1109/RSIP.2017.7958815.
[9]	ZHAO Juanping, ZHANG Zenghui, YU Wenxian, et al. A cascade coupled convolutional neural network guided visual attention method for ship detection from sar images[J]. IEEE Access, 2018, 6: 50 693-50 708.
[10]	TANG Tianyu, ZHOU Shilin, DENG Zhipeng, et al. Arbitrary-oriented vehicle detection in aerial imagery with single convolutional neural networks[J]. Remote Sensing, 2017, 9(11):DOI:10.3390/rs9111170.
[11]	DENG Zhipeng, SUN Hao, ZHOU Shilin, et al. Toward fast and accurate vehicle detection in aerial images using coupled region-based convolutional neural networks[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(8): 3652-3664.
[12]	MANDAL M, SHAH M, MEENA P, et al. AVDNet: a small-sized vehicle detection network for aerial visual data[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(3): 494-498.
[13]	CAI Bowen, JIANG Zhiguo, ZHANG Haopeng, et al. Airport detection using end-to-end convolutional neural network with hard example mining[J]. Remote Sensing, 2017, 9(11):DOI:10.3390/rs9111198.
[14]	HAN Xiaobing, ZHONG Yanfei, ZHANG Liangpei. An efficient and robust integrated geospatial object detection framework for high spatial resolution remote sensing imagery[J]. Remote Sensing, 2017, 9(7): DOI:10.3390/rs9070666.
[15]	LI Ke, CHENG Gong, BU Shuhui, et al. Rotation-insensitive and context-augmented object detection in remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(4): 2337-2348.
[16]	ZOU Zhenxia, SHI Zhenwei. Random access memories: a new paradigm for target detection in high resolution aerial remote sensing images[J]. IEEE Transactions on Image Processing, 2018, 27: 1100-1111. doi: 10.1109/TIP.2017.2773199 pmid: 29220314
[17]	ZHANG Gongjie, LU Shijian, ZHANG Wei. CAD-net: a context-aware detection network for objects in remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(12): 10 015-10 024.
[18]	MA Haojie, LIU Yalan, REN Yuhuan, et al. Detection of collapsed buildings in post-earthquake remote sensing images based on the improved YOLOv3[J]. Remote Sensing, 2019, 12(1):DOI:10.3390/rs12010044.
[19]	HAN Yanling, WEI Cong, ZHOU Ruyan, et al. Combining 3D-CNN and squeeze-and-excitation networks for remote sensing sea ice image classification[J]. Mathematical Problems in Engineering, 2020, 2020(1):1-15.
[20]	ZENG Kan, WANG Yixiao. A deep convolutional neural network for oil spill detection from spaceborne sar images[J]. Remote Sensing, 2020, 12(6):DOI:10.3390/rs12061015.
[21]	BOCHKOVSKIY A, WANG Chienyao, LIAO Hongyuanmark. YOLOv4: optimal speed and accuracy of object detection[J]. ArXiv Preprint, 2020:DOI:10.48550/arXiv.2004.10934.
[22]	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]. Proceedings of the European Conference on Computer Vision (ECCV). 2018: 3-19.
[23]	HE Kaiming, ZHANG Xiangyu, REN Shaoping, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916. doi: 10.1109/TPAMI.2015.2389824 pmid: 26353135
[24]	ZHANG Yifan, REN Weiqiang, ZHANG Zhang, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.

模型	AP/%				mAP@0.5/%	mAP@0.5:0.95/%
模型	田地	绿地	居住地	河流	mAP@0.5/%	mAP@0.5:0.95/%
YOLOv5	49.2	52.1	54.5	1.0	39.2	22.8
YOLOx	59.8	59.1	49.5	17.8	46.6	21.5
YOLOv8	53.5	59.3	58.3	59.1	57.5	24.4
改进模型	62.7	57.8	52.8	99.5	68.2	30.0

序号	注意力机制	损失函数			mAP/%
序号	注意力机制	CIoU	EIoU	Focal	mAP/%
1	未添加CBAM	√	—	—	57.5
2		—	√	—	58.7
3		—	√	√	61.2
4	添加CBAM	√	—	—	59.7
5		—	√	—	67.1
6		—	√	√	68.2

基于改进YOLO模型的中缅油气管道遥感图像高后果区识别方法

High-consequence area indentation of remote sensing images of China-Myanmar oil and gas pipeline based on improved YOLO model

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 24

相关文章 15

编辑推荐

Metrics

本文评价

[1]	夏正洪, 何琥, 杨磊, 吴建军, 刘璐. 基于改进YOLOv8n的飞机铆钉及脱落异常检测算法[J]. 中国安全科学学报, 2025, 35(2): 66-72.
[2]	顾清华, 殷书檀, 王丹, 李学现, 尹慧民. 基于改进YOLOv8的矿卡司机疲劳驾驶检测[J]. 中国安全科学学报, 2025, 35(1): 60-66.
[3]	赵江平, 王欣然, 吴立舟. 改进YOLOv5s的路面坑槽目标检测模型[J]. 中国安全科学学报, 2025, 35(1): 67-74.
[4]	刘惠临, 方琼, 江宇, 魏华章, 王涛, 张树川. 基于YOLOv5s的轻量化森林火灾探测算法[J]. 中国安全科学学报, 2025, 35(1): 75-83.
[5]	孙国思, 马鹏飞, 王威淳, 郜普浩, 朱健伟. 基于YOLOv8算法的露天煤矿大型工程车辆识别与闯入安全预警[J]. 中国安全科学学报, 2024, 34(S1): 191-198.
[6]	雷斌, 闫浪浪, 余华, 温岩, 张亮, 李哲旭. YOLOv5监测算法下轨道交通应急预警感知系统构建[J]. 中国安全科学学报, 2024, 34(9): 225-233.
[7]	吴立舟, 李华, 李典斌, 吴昱锦, 刘攀旺, 薛曦澄. 基于计算机视觉的塔吊危险区域入侵预警[J]. 中国安全科学学报, 2024, 34(7): 139-146.
[8]	李华, 陈兵, 吴立舟, 钟兴润. 基于多尺度特征的消防车道占用检测[J]. 中国安全科学学报, 2024, 34(7): 163-169.
[9]	江松, 李研博, 何旭乾, 何润丰, 张超, 张存良. 基于无人机影像深度学习的滑坡灾害智能识别[J]. 中国安全科学学报, 2024, 34(7): 229-238.
[10]	纪执安, 周云奕, 张玉媛, 郭新然, 石坤. 基于改进YOLOv5的工业现场不安全行为检测[J]. 中国安全科学学报, 2024, 34(7): 38-43.
[11]	贾桂敏, 程羽, 齐孟飞. 多尺度注意力特征增强融合的红外小目标检测新网络[J]. 中国安全科学学报, 2024, 34(6): 90-98.
[12]	张明振, 段江忠, 梁肇伟, 郭俊杰, 柴大山. 基于改进YOLO-V5算法的烟火检测方法[J]. 中国安全科学学报, 2024, 34(5): 155-161.
[13]	周军超, 陈鑫, 高建杰, 章杰. 基于改进YOLOv8n算法的城市空间混行交通参与者检测模型[J]. 中国安全科学学报, 2024, 34(12): 178-186.
[14]	张术琳, 张亚楠, 田超, 严翔, 鲁义, 施式亮. 基于CNN的化工园区火灾火焰图像识别研究[J]. 中国安全科学学报, 2024, 34(1): 179-186.
[15]	魏德志, 杜志勇, 滕春阳, 辛吴天, 李泽坤. 露天矿破碎站链条断裂安全监测技术研究[J]. 中国安全科学学报, 2023, 33(S2): 170-175.