Hyperspectral Image Detection of Gasoline Pipeline Leakage Using
Improved Unet Network
WANG Ke-ming1, GONG Wei-jia1, WANG Hai-ming2, CAI Yong-jun2, LIU Jia-xing3, SUN Lei4, SONG Li-mei1, LI Jin-yi1*
1. Tianjin Key Laboratory of Intelligent Control of Electrical Equipment, School of Control Science and Engineering, Tiangong University, Tianjin 300387, China
2. Science and Technology Research Institute Branch, National Oil and Gas Pipeline Network Group Co., Ltd., Tianjin 300450, China
3. Northern Pipeline LLC, National Oil and Gas Pipeline Network Group Co., Ltd., Langfang 065000, China
4. Shandong Branch, National Oil and Gas Pipeline Network Group Co., Ltd., Jinan 250000, China
Abstract：In view of the limitations of the low efficiency of gasoline pipeline leak detection and the inability to accurately segment the edge of the leak region, a gasoline pipeline leak detection method is proposed based on hyperspectral image and deep learning. Firstly, the characteristic spectral bands of the two types of gasoline under the background of soil and water were extracted. The continuous projection algorithm was used to reduce the dimensionality of gasoline hyperspectral image data. The gasoline reflectivity was taken as input, and the root-mean-square error was the regression parameter used to obtain 18 characteristic bands near the gasoline reflection peak. Image rotation Angle, horizontal or vertical inversion, and random noise injection into the image are used to expand the dataset sample. Secondly, the Unet hyperspectral image semantic segmentation model is improved, and the network encoder part of Unet is replaced with a dense connection module to strengthen the information exchange between different levels, reduce the computational load, and improve the model detection speed. The spectral attention mechanism module is introduced to make the model pay attention to gasoline image space and spectral features and improve the model detection accuracy. The concept of an inactivation layer is introduced to reduce the complexity of the network by temporarily shutting down some neurons in the network. At the same time, an appropriate time point is set in the training process to implement the early stop strategy to prevent overfitting. Finally, the ablation experiment and comparison experiment were carried out. The results of ablation experiments validate the effectiveness of the dense connection module and the spectral attention mechanism module in improving the network's segmentation accuracy and recall rate. Quantitative comparison experiments on self-built data sets show that the segmentation accuracy of the proposed model for dripping gasoline is 90.34%, and the average detection time of each image is 0.23 s. Compared with Unet, PSE-Unet, and HLCA-Unet models, the average accuracy is increased by 14.39%, 8.01%, and 2.73%, respectively. The recall rate was increased by 8.95%, 8.02%, and 6.55%, and the test time was reduced by 10.83% and 16.97%, respectively, compared with Unet and PSE-Unet models. The qualitative superiority of detection was reflected in the intersection profile of gasoline and background being more consistent with the original image, and the model in this paper could obtain more accurate analysis information of gasoline characteristics. It provides a new technical scheme for gasoline pipeline leakage detection. In addition, compared with the detection of current Unet, PSE-Unet, and HLCA-Unet models on the open Pavia University remote sensing data set, the proposed model still shows better segmentation effect and strong universality and generalization ability; it can be used for many types of hyperspectral image semantic segmentation.
王克明，公维佳，王海明，蔡永军，刘嘉星，孙 磊，宋丽梅，李金义. 改进Unet网络的汽油管道泄漏高光谱图像检测[J]. 光谱学与光谱分析, 2025, 45(05): 1476-1484.
WANG Ke-ming, GONG Wei-jia, WANG Hai-ming, CAI Yong-jun, LIU Jia-xing, SUN Lei, SONG Li-mei, LI Jin-yi. Hyperspectral Image Detection of Gasoline Pipeline Leakage Using
Improved Unet Network. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(05): 1476-1484.
[1] PENG Yang(彭 扬). Oil Refining Technology and Engineering（炼油技术与工程）, 2024, 54(1): 59.
[2] WANG Yu-qin(王禹钦). Petroleum Knowledge(石油知识), 2021，(3): 32.
[3] CHEN Meng(陈 萌). Science and Technology Innovation and Application(科技创新与应用), 2023, 13(25): 182.
[4] Rougier J. Journal of Hydraulic Research, 2005, 43(5): 556.
[5] LIU Ai-ming, LIANG Peng, FENG Yuan, et al(刘爱明, 梁 鹏, 封 园, 等). Petro & Chemical Equipment(石油和化工设备), 2024, 27(4): 156.
[6] Lang X, Zhu Y. Measurement Science and Technology, 2022, 33(12): 125108.
[7] Yang Y, Du Z, Li Y, et al. Advances in Civil Engineering, 2022, 2022(9): 11.
[8] Xie J, Zhang Y, He Z, et al. Process Safety and Environmental Protection, 2023, 174: 39.
[9] Usamentiaga R. IEEE Transactions on Industrial Informatics, 2024, 20(2): 2540.
[10] Krapez J C, Sanchis Muñoz J, Mazel C, et al. Sensors, 2022, 22(3): 1057.
[11] YANG Zeng-rong, WANG Huai-bin, TIAN Mi-mi, et al(杨增荣, 王怀彬, 田密密, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2024, 44 (5): 1364.
[12] Pietrapertosa C, Spisni A, Pancioli V, et al. Bollettino di Geofisica Teorica ed Applicata, 2016, 57(1): 31.
[13] ZHANG Bing(张 兵). National Remote Sensing Bulletin(遥感学报), 2016, 20(5): 1062.
[14] Liu B, Li Y, Li G, et al. ISPRS International Journal of Geo-Information, 2019, 8(4): 160.
[15] Qin H, Dong Y, Cui H, et al. Analytical Letters, 2024, 57(18): 3068.
[16] Zhan C, Bai K, Tu B, et al. Sensors, 2024, 24(2): 411.
[17] Qing Y, Liu W. Remote Sensing, 2021, 13(3): 335.
[18] Vaswani A, Shazeer N, Parmar N, et al. Attention is All You Need, 31st Conference on Neural Information Processing Systems, 2017.
[19] Li J, Wang H, Zhang A, et al. Sensors, 2022, 22(24): 9678.
[20] Gao H, Yang M, Cao X, et al. Machine Vision and Applications, 2023, 34(5): 72.
