浏览全部资源
扫码关注微信
1.中国计量大学 光学与电子科技学院,浙江 杭州 310018
2.西安应用光学研究所,陕西 西安710065
Received:01 August 2022,
Revised:20 September 2022,
Published:10 April 2023
移动端阅览
曾子威,金尚忠,李宏光等.高湿度环境下爆炸物太赫兹光谱的特征提取与精准识别[J].光学精密工程,2023,31(07):1065-1073.
ZENG Ziwei,JIN Shangzhong,LI Hongguang,et al.Terahertz spectral features detection and accuracy identification of explosives in high humidity environment[J].Optics and Precision Engineering,2023,31(07):1065-1073.
曾子威,金尚忠,李宏光等.高湿度环境下爆炸物太赫兹光谱的特征提取与精准识别[J].光学精密工程,2023,31(07):1065-1073. DOI: 10.37188/OPE.20233107.1065.
ZENG Ziwei,JIN Shangzhong,LI Hongguang,et al.Terahertz spectral features detection and accuracy identification of explosives in high humidity environment[J].Optics and Precision Engineering,2023,31(07):1065-1073. DOI: 10.37188/OPE.20233107.1065.
材料太赫兹吸收谱的指纹特性已被广泛应用于物质识别,但实际大气环境下,水蒸气对太赫兹波的强烈吸收会导致光谱严重振荡,假峰、弱峰、混叠峰相继增多,严重影响寻峰比对的精度及物质识别的能力。针对上述问题,提取相对湿度为2%,15%,35%,45%和60%环境下爆炸物的太赫兹吸收光谱信息数据,利用连续小波变换将光谱在频域上展开得到具有特征唯一性的频域尺度图;再基于深度学习方法,以ResNet-50网络模型为基本网络结构,对上述5种不同湿度环境下得到的爆炸物频域尺度图进行网络分类训练,其测试集分类准确率达96.6%。为验证该技术在未经训练湿度样本下的有效性,将相对湿度为50%,55%和67%时爆炸物的时域信号送入该识别系统,分类准确率可达96.2%。实验结果表明,基于小波变换与ResNet-50网络分类训练的太赫兹物质识别方法相比于传统寻峰方法大幅提升了爆炸物在高湿度环境下的识别准确率,规避了降噪、平滑等一系列复杂预处理操作,极大拓展了太赫兹光谱探测技术的工程适应性,为山地、森林、洼地等高湿度、极复杂的作战环境下精确探测、识别地雷等爆炸物提供了技术支持。
The fingerprint characteristics of the terahertz absorption spectrum of materials have been widely used in material identification, but the strong absorption of terahertz waves by water vapor in the actual atmospheric environment will cause the spectrum to oscillate severely; there will be increasing false, weak, and aliased peaks. These phenomena have seriously affected the accuracy of peak-finding comparison and the ability of substance identification. In spite of this, on the basis of extracting the terahertz absorption spectrum of explosives at relative humidity of 2%, 15%, 35%, 45%, and 60%, the continuous wavelet transform is expanded in the frequency domain to obtain a unique characteristic. Then, the network training is carried out on the frequency domain scale maps of explosives obtained under the above 5 different humidity conditions based on the deep learning method with the ResNet-50 network model as the basic network structure; the classification accuracy of the test can be up to 96.6%. To verify the effectiveness of the technology under untrained humidity samples, the time-domain signals of explosives at relative humidity of 50%, 55%, and 67% were fed into the identification system; the classification accuracy could reach 96.2%. Experiments show that a new terahertz material identification method, based on wavelet transform and ResNet-50 network classification training, greatly improves the accuracy of material identification in high humidity environment compared with the traditional peak-finding method. In addition, it avoids a series of complex preprocessing operations such as noise reduction and smoothing, and considerably expands the engineering adaptability of terahertz spectral detection technology. It provides help for accurate detection and identification of mines and other explosives in high humidity and extremely complex special operations environments such as mountains, forests, and depressions.
FU X J , LIU Y J , CHEN Q , et al . Applications of terahertz spectroscopy in the detection and recognition of substances [J]. Frontiers in Physics , 2022 , 10 : 869537 . doi: 10.3389/fphy.2022.869537 http://dx.doi.org/10.3389/fphy.2022.869537
李宏光 , 杨鸿儒 , 薛战理 , 等 . 窄带光谱滤光法探测低温黑体太赫兹辐射 [J]. 光学 精密工程 , 2013 , 21 ( 6 ): 1410 - 1416 . doi: 10.3788/ope.20132106.1410 http://dx.doi.org/10.3788/ope.20132106.1410
LI H G , YANG H R , XUE ZH L , et al . Terahertz radiation detection of low temperature blackbody based on narrowband spectral filter method [J]. Opt. Precision Eng. , 2013 , 21 ( 6 ): 1410 - 1416 . (in Chinese) . doi: 10.3788/ope.20132106.1410 http://dx.doi.org/10.3788/ope.20132106.1410
解琪 , 杨鸿儒 , 李宏光 , 等 . 基于太赫兹时域光谱系统的爆炸物识别 [J]. 光学 精密工程 , 2016 , 24 ( 10 ): 2392 - 2399 . doi: 10.3788/ope.20162410.2392 http://dx.doi.org/10.3788/ope.20162410.2392
XIE Q , YANG H R , LI H G , et al . Explosive identification based on terahertz time-domain spectral system [J]. Opt. Precision Eng. , 2016 , 24 ( 10 ): 2392 - 2399 . (in Chinese) . doi: 10.3788/ope.20162410.2392 http://dx.doi.org/10.3788/ope.20162410.2392
PAL S , CHATTOPADHYAY A . Hydration dynamics in biological membranes: emerging applications of terahertz spectroscopy [J]. The Journal of Physical Chemistry Letters , 2021 , 12 ( 39 ): 9697 - 9709 . doi: 10.1021/acs.jpclett.1c02576 http://dx.doi.org/10.1021/acs.jpclett.1c02576
刘欣缘 , 曾昊旻 , 田昕 , 等 . 太赫兹辐射在皮肤中的传输仿真与安全性分析 [J]. 光学 精密工程 , 2021 , 29 ( 5 ): 999 - 1007 . doi: 10.37188/OPE.20212905.0999 http://dx.doi.org/10.37188/OPE.20212905.0999
LIU X Y , ZENG H M , TIAN X , et al . Transmission simulation and safety analysis of terahertz radiation in skin [J]. Opt. Precision Eng. , 2021 , 29 ( 5 ): 999 - 1007 . (in Chinese) . doi: 10.37188/OPE.20212905.0999 http://dx.doi.org/10.37188/OPE.20212905.0999
许景周 , 张希成 . 太赫兹科学技术和应用 [M]. 北京 : 北京大学出版社 , 2007 : 1 - 248 .
XU J ZH , ZHANG X CH . Terahertz Science and Technology and its Application [M]. Beijing : Peking University Press , 2007 : 1 - 248 . (in Chinese)
VAN EXTER M , FATTINGER C , GRISCHKOWSKY D . Terahertz time-domain spectroscopy of water vapor [J]. Optics Letters , 1989 , 14 ( 20 ): 1128 - 1130 . doi: 10.1364/ol.14.001128 http://dx.doi.org/10.1364/ol.14.001128
姚宝岱 , 王高 . 基于小波变换的爆炸物太赫兹光谱降噪分析 [J]. 光电技术应用 , 2011 , 26 ( 1 ): 63 - 65 . doi: 10.3969/j.issn.1673-1255.2011.01.018 http://dx.doi.org/10.3969/j.issn.1673-1255.2011.01.018
YAO B D , WANG G . Denoising analysis of terahertz spectra of explosives based on wavelet transform [J]. Electro-Optic Technology Application , 2011 , 26 ( 1 ): 63 - 65 . (in Chinese) . doi: 10.3969/j.issn.1673-1255.2011.01.018 http://dx.doi.org/10.3969/j.issn.1673-1255.2011.01.018
王迎新 , 陈志强 , 赵自然 , 等 . 基于太赫兹时域谱分析的爆炸物检测方法研究 [J]. 光学技术 , 2007 , 33 ( 4 ): 587 - 590 . doi: 10.3321/j.issn:1002-1582.2007.04.014 http://dx.doi.org/10.3321/j.issn:1002-1582.2007.04.014
WANG Y X , CHEN ZH Q , ZHAO Z R , et al . Study on the method of explosives detection based on terahertz time-domain spectroscopy [J]. Optical Technique , 2007 , 33 ( 4 ): 587 - 590 . (in Chinese) . doi: 10.3321/j.issn:1002-1582.2007.04.014 http://dx.doi.org/10.3321/j.issn:1002-1582.2007.04.014
NI J P , SHEN T , ZHU Y , et al . Terahertz spectroscopic identification with diffusion maps [J]. Spectroscopic identification with diffusion maps , 2017 , 37 ( 8 ): 2360 - 2364 .
LIU W Q , ZHANG R , LING Y , et al . Automatic recognition of breast invasive ductal carcinoma based on terahertz spectroscopy with wavelet packet transform and machine learning [J]. Biomedical Optics Express , 2020 , 11 ( 2 ): 971 - 981 . doi: 10.1364/boe.381623 http://dx.doi.org/10.1364/boe.381623
DORNEY T D , BARANIUK R G , MITTLEMAN D M . Material parameter estimation with terahertz time-domain spectroscopy [J]. Journal of the Optical Society of America A, Optics, Image Science, and Vision , 2001 , 18 ( 7 ): 1562 - 1571 . doi: 10.1364/josaa.18.001562 http://dx.doi.org/10.1364/josaa.18.001562
GUO T T , ZHANG T P , LIM E , et al . A review of wavelet analysis and its applications: challenges and opportunities [J]. IEEE Access , 2022 , 10 : 58869 - 58903 . doi: 10.1109/access.2022.3179517 http://dx.doi.org/10.1109/access.2022.3179517
DAUBECHIES I . Ten Lectures on Wavelets [M]. SIAM , Philadelphia , 1992 . doi: 10.1137/1.9781611970104 http://dx.doi.org/10.1137/1.9781611970104
HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2730,2016 , Las Vegas, NV, USA. IEEE , 2016 : 770 - 778 . doi: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90
IEEE transactions on terahertz science and technology [J]. IEEE Transactions on Terahertz Science and Technology , 2018 , 8 ( 4 ): C3 - C3 . doi: 10.1109/tthz.2018.2846380 http://dx.doi.org/10.1109/tthz.2018.2846380
LIU H B , ZHONG H , KARPOWICZ N , et al . Terahertz spectroscopy and imaging for defense and security applications [C]. Proceedings of the IEEE . 2007 , IEEE , 2007 : 1514 - 1527 . doi: 10.1109/jproc.2007.898903 http://dx.doi.org/10.1109/jproc.2007.898903
DENG J , DONG W , SOCHER R , et al . ImageNet: a large-scale hierarchical image database [C]. 2009 IEEE Conference on Computer Vision and Pattern Recognition . 2025,2009 , Miami , FL, USA . IEEE , 2009 : 248 - 255 . doi: 10.1109/cvpr.2009.5206848 http://dx.doi.org/10.1109/cvpr.2009.5206848
0
Views
499
下载量
4
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution