为了实现海关对高含水率违禁品的非侵入快速筛查,提出了一种电容层析成像(ECT)技术与深度学习相结合的检测方法,在仿真环境下进行了可行性研究。首先,设计了适合安装在传送装置上的ECT传感器,并构建了分别含有正常物体和高含水率违禁品的不同包裹模型;然后,利用电容传感器获得不同包裹模型的电容信号数据,并进行二维和三维图像重建;最后,为了弥补人工观察包裹重建图像误判率高的缺陷,构建了自适应提取电容信号特征的一维卷积神经网络(1D-CNN)模型对包裹模型进行预测分类。实验结果表明:该方法的检测准确率可达98%以上,单个模型检测时间仅为10-3s,能够实现高含水率违禁品的快速筛查。
Abstract
In order to realize the non-invasive and rapid screening of high moisture content contraband by the customs, a detection method combining electrical capacitance tomography (ECT) technology and deep learning is proposed, and the feasibility study is carried out in the simulation environment. Firstly, the ECT sensor suitable for installation on the conveyor is designed, and different package models containing normal objects and contraband with high moisture content are constructed; Then, the capacitance signal data of different package models are obtained by capacitance sensor, and the two-dimensional and three-dimensional image reconstruction are carried out; Finally, in order to make up for the high error rate of manually observed package reconstruction image, a one-dimensional convolutional neural network (1D-CNN) model for adaptive extraction of capacitance signal features is constructed to predict and classify the package model. The experimental results show that the detection accuracy of the proposed method can reach over 98%, and the detection time of a single model is only 10-3 seconds, which can achieve rapid screening of high moisture content prohibited substances.
关键词
计量学 /
含水率 /
违禁品检测 /
深度学习 /
快速筛查 /
ECT传感器
Key words
metrology;moisture content /
contraband detection;deep learning;rapid screening;ECT sensor
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］王佳翔. 天津海关安全监管问题研究［D］. 秦皇岛: 燕山大学, 2020.
［2］梁添汾, 张南峰, 张艳喜, 等. 违禁品X光图像检测技术应用研究进展综述［J］. 计算机工程与应用, 2021, 57(16): 74-82.
Liang T F, Zhang N F, Zhang Y X, et al. Summary of research progress on application of prohibited item detection in X-ray images［J］. Computer Engineering and Applications, 2021, 57(16): 74-82.
［3］蒋林华, 王尉苏, 童慧鑫, 等. 太赫兹成像技术在人体安检领域的研究进展［J］. 上海理工大学学报, 2019, 41(1): 46-51.
Jiang L H, Wang W S, Tong H X, et al. Research progress of terahertz imaging in the field of human security［J］. Journal of University of Shanghai for Science and Technology, 2019, 41(1): 46-51.
［4］Perot B, Carasco C, Bernard S, et al. Development of the EURITRACK tagged neutron inspection system［J］. Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, 2007, 261(1-2): 295-298.
［5］费鹏, 方维海, 温鑫, 等. 用于人员安检的主动毫米波成像技术现状与展望［J］. 微波学报, 2015, 31(2): 91-96.
Fei P, Fang W H, Wen X, et al. State of the Art and Future Prospect of the Active Millimeter Wave Imaging Technique for personnel screening［J］. Journal of Microwaves, 2015, 31(2): 91-96.
［6］Ye Z, Robert B, Soleimani M. Planar Array 3D Electrical Capacitance Tomography［J］. Insight: Non-Destructive Testing and Condition Monitoring, 2013, 55(12): 675-680.
［7］马敏, 王涛. 基于CNN-MSLSTM的航空发动机滑油监测方法研究［J］. 计量学报, 2021, 42(2): 232-238.
Ma M, Wang T. Research on Monitoring Method of Aeroengine Lubricating Oil Based on CNN-MSLSTM［J］. Acta Metrologica Sinica, 2021, 42(2): 232-238.
［8］Wei K, Qiu C H, Primrode K. Super-sensing Technology: Industrial Applications and Future Challenges of Electrical Tomography［J］. Philosophical transactions. Series A, Mathematical, physical, and engineering sciences, 2016, 374(2070): 20150328.
［9］季厌庸, 刘亚楠, 邓晨肖, 等. 基于ECT的航空复合材料缺陷检测研究［J］. 计量学报, 2019, 40(6): 952-957.
Ji Y Y, Liu Y N, Deng C X, et al. Research on the Testing of Adhesive Defects of Aeronautical Composites Based on ECT［J］. Acta Metrologica Sinica, 2019, 40(6): 952-957.
［10］张立峰, 戴力. 基于鲁棒正则化极限学习机的电容层析成像图像重建［J］. 计量学报, 2022, 43(8): 1044-1049.
Zhang L F, Dai L. Image Reconstruction Based on Robust Regularized Extreme Learning Machine for Electrical Capacitance Tomography［J］. Acta Metrologica Sinica, 2022, 43(8): 1044-1049.
［11］Gu J, Wang Z, Kuen J, et al. Recent Advances in Convolutional Neural Networks［J］. Pattern Recognition, 2018, 77(4): 354-377.
［12］张世辉, 王红蕾, 陈宇翔, 等. 基于深度学习利用特征图加权融合的目标检测方法［J］. 计量学报, 2020, 41(11): 1344-1351.
Zhang S H, Wang H L, Chen Y X, et al. An Object Detection Method Based on Deep Learning Using Feature Map Weighted Fusion［J］. Acta Metrologica Sinica, 2020, 41(11): 1344-1351.
［13］曲建岭, 余路, 袁涛, 等. 基于一维卷积神经网络的滚动轴承自适应故障诊断算法［J］. 仪器仪表学报, 2018, 39(7): 134-143.
Qu J L, Yu L, Yuan T, et al. Adaptive Fault Diagnosis Algorithm for Rolling Bearings Based on One-dimensional Convolutional Neural Network［J］. Chinese Journal of Scientific Instrument, 2018, 39(7): 134-143.
［14］Steitz J O M, Saeedan F, Roth S. Multi-view x-ray r-cnn［C］// German Conference on Pattern Recognition. Springer, Cham,Switzerland, 2018: 153-168.
［15］张友康, 苏志刚, 张海刚, 等. X光安检图像多尺度违禁品检测［J］. 信号处理, 2020, 36(7): 1096-1106.
Zhang Y K, Su Z G, Zhang H G, et al. Multi-scale Prohibited Item Detection in X-ray Security Image［J］. Journal of Signal Processing, 2020, 36(7): 1096-1106.
［16］Hu X, Yang W. Planar Capacitive Sensors-Designs and Applications［J］. Sensor Review, 2010, 30(1): 24-39.
［17］Feng H, Tang J, Cavalieri R P. Dielectric Properties of Dehydrated App Les as Affected by Moisture and Temperature［J］. Transactions of the ASAE, 2002, 45 (1): 129-135.
［18］金列俊, 詹建明, 陈俊华, 等. 基于一维卷积神经网络的钻杆故障诊断［J］. 浙江大学学报(工学版), 2020, 54(3): 467-474.
Jin L J, Zhan J M, Chen J H, et al. Drill Pipe Fault Diagnosis Method Based on One-dimensional Convolutional Neural Network［J］. Journal of Zhejiang University(Engineering Science), 2020, 54(3): 467-474.
［19］崔自强, 王化祥. 提高电容层析成像系统实时性研究［J］. 仪器仪表学报, 2010, 31(9): 1939-1945.
Cui Z Q, Wang H X. Improvements on Real-time Performance of Electrical Capacitance Tomography［J］. Chinese Journal of Scientific Instrument, 2010, 31(9): 1939-1945.
基金
国家自然科学基金 (61871379);天津市教委科研计划 (2020KJ012)
PDF(660 KB)
