{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T18:01:42Z","timestamp":1780596102240,"version":"3.54.1"},"reference-count":53,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2020,9,2]],"date-time":"2020-09-02T00:00:00Z","timestamp":1599004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Sciences Foundation of China","award":["61771372"],"award-info":[{"award-number":["61771372"]}]},{"name":"National Natural Sciences Foundation of China","award":["61771367"],"award-info":[{"award-number":["61771367"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Millimeter-wave (MMW) imaging scanners can see through clothing to form a three-dimensional holographic image of the human body and suspicious objects, providing a harmless alternative for non-contacting searches in security check. Suspicious object detection in MMW images is challenging, since most of them are small, reflection-weak, shape, and reflection-diverse. Conventional detectors with artificial neural networks, like convolution neural network (CNN), usually take the problem of finding suspicious objects as an object recognition task, yielding difficulties in developing large-amount and complete sample sets of objects. In this paper, a new algorithm is developed using the human pose segmentation followed by the deep CNN detection. The algorithm is emphasized to learn the similarity with humans\u2019 body clutter applied to training corresponding CNNs after the image segmentation base of the pose estimation. Moreover, the suspicious object recognition in the MMW image is converted to a binary classification task. Instead of recognizing all sorts of suspicious objects, the CNN detector determines whether the body part images present the abnormal patterns containing suspicious objects. The proposed algorithm that is based on CNN with the pose segmentation has concise configuration, but optimal performance in the suspicious object detection. Extensive experiments confirm the effectiveness and superiority of the proposal.<\/jats:p>","DOI":"10.3390\/s20174974","type":"journal-article","created":{"date-parts":[[2020,9,2]],"date-time":"2020-09-02T09:29:28Z","timestamp":1599038968000},"page":"4974","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["CNN with Pose Segmentation for Suspicious Object Detection in MMW Security Images"],"prefix":"10.3390","volume":"20","author":[{"given":"Zhichao","family":"Meng","sequence":"first","affiliation":[{"name":"National Laboratory of Radar Signal Processing, Xidian University, Xi\u2019an 710071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Man","family":"Zhang","sequence":"additional","affiliation":[{"name":"The School of Physics and Electronic Engineering, Guangzhou University, Guangzhou 510006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxian","family":"Wang","sequence":"additional","affiliation":[{"name":"National Laboratory of Radar Signal Processing, Xidian University, Xi\u2019an 710071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,9,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Agurto, A., Li, Y., Tian, G.Y., Bowring, N., and Lockwood, S. (2007, January 15\u201317). A review of concealed weapon detection and research in perspective. Proceedings of the 2007 IEEE International Conference on Networking, Sensing and Control, London, UK.","DOI":"10.1109\/ICNSC.2007.372819"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sheen, D.M., McMakin, D.L., and Hall, T.E. (1997, January 15\u201317). Cylindrical millimeter-wave imaging technique for concealed weapon detection. Proceedings of the 26th AIPR Workshop: Exploiting New Image Sources and Sensors, Washington, DC, USA.","DOI":"10.1117\/12.300061"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1109\/22.942570","article-title":"Three-dimensional millimeter-wave imaging for concealed weapon detection","volume":"49","author":"Sheen","year":"2001","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1109\/TMTT.2018.2880757","article-title":"Combining commercially available active and passive sensors into a millimeter-wave image for concealed weapon detection","volume":"67","author":"Montesano","year":"2019","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1049\/iet-map.2009.0330","article-title":"Millimeter wave imaging system parameters at 95 GHz","volume":"5","author":"Zhang","year":"2011","journal-title":"IET Microw. Antennas Propag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4948","DOI":"10.1109\/JSEN.2013.2273487","article-title":"Active millimeter wave sensor for standoff concealed threat detection","volume":"13","author":"Andrews","year":"2013","journal-title":"IEEE Sens. J."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Elboushi, A., and Sebak, A. (2012, January 10\u201312). Active millimeter-wave imaging system for hidden weapons detection. Proceedings of the 29th National Radio Science Conference (NRSC), Cairo, Egypt.","DOI":"10.1109\/NRSC.2012.6208514"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1117\/12.142900","article-title":"Near-field millimeter-wave imaging for weapons detection","volume":"Volume 1824","author":"Sheen","year":"1993","journal-title":"Applications of Signal and Image Processing in Explosives Detection Systems"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"E83","DOI":"10.1364\/AO.49.000E83","article-title":"Near-field three-dimensional radar imaging techniques and applications","volume":"49","author":"Sheen","year":"2010","journal-title":"Appl. Opt."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"98290V","DOI":"10.1117\/12.2229235","article-title":"Three dimensional radar imaging techniques and systems for near-field applications","volume":"Volume 9829","author":"Sheen","year":"2016","journal-title":"Radar Sensor Technology XX"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1049\/iet-rsn.2009.0029","article-title":"Interferometric focusing for the imaging of humans","volume":"4","author":"Bertl","year":"2010","journal-title":"IET Radar Sonar Navig."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1018902","DOI":"10.1117\/12.2262476","article-title":"Millimeter wave imaging: A historical review","volume":"Volume 10189","author":"Appleby","year":"2017","journal-title":"Passive and Active Millimeter-Wave Imaging XX"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"10659","DOI":"10.1364\/OE.18.010659","article-title":"Automatic image segmentation for concealed object detection using the expectation-maximization algorithm","volume":"18","author":"Lee","year":"2010","journal-title":"Opt. Express"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"9371","DOI":"10.1364\/OE.20.009371","article-title":"Real-time concealed-object detection and recognition with passive millimeter wave imaging","volume":"20","author":"Yeom","year":"2012","journal-title":"Opt. Express"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yu, C.C., Zhang, G.F., and Gao, Y. (2019., January 27\u201328). Improved threshold-based segmentation method for millimeter wave radiometric image. Proceedings of the 2019 International Conference on Modeling, Simulation, Optimization and Numerical Techniques (SMONT 2019), Shenzhen, China.","DOI":"10.2991\/smont-19.2019.38"},{"key":"ref_16","first-page":"4736","article-title":"An automatic hybrid Approach to Detect Concealed Weapons Using Deep Learning","volume":"12","year":"2017","journal-title":"ARPN J. Eng. Appl. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.engappai.2017.09.005","article-title":"Using machine learning to detect and localize concealed objects in passive millimeter-wave images","volume":"67","author":"Tapia","year":"2018","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3134","DOI":"10.1364\/AO.58.003134","article-title":"Real-time concealed object detection and recognition in passive imaging at 250 GHz","volume":"58","author":"Kowalski","year":"2019","journal-title":"Appl. Opt."},{"key":"ref_19","first-page":"4224","article-title":"Potential active shooter detection based on radar micro-doppler and range-doppler analysis using artificial neural network","volume":"13","author":"Li","year":"2013","journal-title":"IEEE Sens. J."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1002\/mop.31005","article-title":"An auto-classification procedure for concealed weapon detection in millimeter-wave radiometric imaging systems","volume":"60","author":"Isiker","year":"2018","journal-title":"Microw. Opt. Technol. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Maqueda, I.G., de la Blanca, N.P., Molina, R., and Katsaggelos, A.K. (September, January 31). Fast millimeter wave threat detection algorithm. Proceedings of the 2015 23rd European Signal Processing Conference (EUSIPCO), Nice, France.","DOI":"10.1109\/EUSIPCO.2015.7362453"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Martinez, O., Ferraz, L., Binefa, X., Gomez, I., and Dorronsoro, C. (2010, January 13\u201318). Concealed object detection and segmentation over millimetric waves images. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, San Francisco, CA, USA.","DOI":"10.1109\/CVPRW.2010.5543714"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yeom, S., Lee, D.S., Son, J.Y., and Kim, S.H. (2010, January 18\u201319). Concealed object detection using passive millimeter wave imaging. Proceedings of the 2010 4th International Universal Communication Symposium, Beijing, China.","DOI":"10.1109\/IUCS.2010.5666180"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2465","DOI":"10.1109\/TIP.2008.2006662","article-title":"Detection and segmentation of concealed objects in terahertz images","volume":"17","author":"Shen","year":"2008","journal-title":"IEEE Trans. Image Process."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2530","DOI":"10.1364\/OE.19.002530","article-title":"Real-time outdoor concealed-object detection with passive millimeter wave imaging","volume":"19","author":"Yeom","year":"2011","journal-title":"Opt. Express"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1007\/s10762-015-0146-8","article-title":"Segmentation of concealed objects in passive millimeter-wave images based on the Gaussian mixture model","volume":"36","author":"Yu","year":"2015","journal-title":"J. Infrared Millim. Terahertz Waves"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"95850R","DOI":"10.1117\/12.2189299","article-title":"New way for both quality enhancement of THz images and detection of concealed objects","volume":"Volume 9585","author":"Trofimov","year":"2015","journal-title":"Terahertz Emitters, Receivers, and Applications VI"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Sugiyama, M. (2015). Introduction to Statistical Machine Learning, Morgan Kaufmann.","DOI":"10.1016\/B978-0-12-802121-7.00012-1"},{"key":"ref_29","unstructured":"Ganapathi, A.S. (2009). Predicting and Optimizing System Utilization and Performance via Statistical Machine Learning. [Ph.D. Thesis, University of California]."},{"key":"ref_30","first-page":"307","article-title":"Challenges in statistical machine learning","volume":"16","author":"Lafferty","year":"2006","journal-title":"Stat. Sin."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 24\u201327). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_32","unstructured":"Ren, S., He, K.M., Girshick, R., and Sun, J. (2015, January 7\u201312). Faster R-CNN: Towards real-time object detection with region proposal networks. Proceedings of the Advances in Neural Information Processing Systems 28 (NIPS 2015), Montreal, QC, Canada."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","article-title":"Mask R-CNN","volume":"42","author":"He","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4395","DOI":"10.1109\/TIM.2019.2941292","article-title":"Detection Approach Based on an Improved Faster RCNN for Brace Sleeve Screws in High-Speed Railways","volume":"69","author":"Liu","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3262","DOI":"10.1109\/TIM.2019.2928347","article-title":"Visual Defect Inspection for Deep-Aperture Components with Coarse-to-Fine Contour Extraction","volume":"69","author":"Gong","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1109\/TCPMT.2019.2952393","article-title":"Solder Joint Recognition Using Mask R-CNN Method","volume":"10","author":"Wu","year":"2020","journal-title":"IEEE Trans. Compon. Packag. Manuf. Technol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"5301","DOI":"10.1109\/TIP.2020.2975711","article-title":"Outdoor RGBD Instance Segmentation with Residual Regretting Learning","volume":"29","author":"Xu","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Tapia, S.L., Molina, R., and de la Blanca, N.P. (September, January 29). Detection and localization of objects in passive millimeter wave images. Proceedings of the 2016 24th European Signal Processing Conference (EUSIPCO), Budapest, Hungary.","DOI":"10.1109\/EUSIPCO.2016.7760619"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2580","DOI":"10.1109\/TCSVT.2017.2774927","article-title":"Deep CNNs for object detection using passive millimeter sensors","volume":"29","author":"Tapia","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Yuan, J.X., and Guo, C.G. (July, January 30). A deep learning method for detection of dangerous equipment. Proceedings of the 2018 Eighth International Conference on Information Science and Technology (ICIST), Cordoba, Spain.","DOI":"10.1109\/ICIST.2018.8426165"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1007\/s10762-018-0558-3","article-title":"High-performance detection of concealed forbidden objects on human body with deep neural networks based on passive millimeter wave and visible imagery","volume":"40","author":"Guo","year":"2019","journal-title":"J. Infrared Millim. Terahertz Waves"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"9909","DOI":"10.1109\/TIE.2019.2893843","article-title":"Concealed object detection for activate millimeter wave image","volume":"66","author":"Liu","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"87","DOI":"10.2528\/PIER18012601","article-title":"Towards robust human millimeter wave imaging inspection system in real time with deep learning","volume":"161","author":"Liu","year":"2018","journal-title":"Prog. Electromagn. Res."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhang, J.S., Xing, W.J., Xing, M.D., and Sun, G.C. (2018). Terahertz image detection with the improved faster region-based convolutional neural network. Sensors, 18.","DOI":"10.3390\/s18072327"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.sigpro.2019.02.029","article-title":"CNN with spatio-temporal information for fast suspicious object detection and recognition in THz security images","volume":"160","author":"Yang","year":"2019","journal-title":"Signal Process."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Pang, L., Liu, H., Chen, Y., and Miao, J. (2020). Real-time Concealed Object Detection from Passive Millimeter Wave Images Based on the YOLOv3 Algorithm. Sensors, 20.","DOI":"10.3390\/s20061678"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"131","DOI":"10.2528\/PIERL15081007","article-title":"Shape feature analysis of concealed objects with passive millimeter wave imaging","volume":"57","author":"Yeom","year":"2015","journal-title":"Prog. Electromagn. Res."},{"key":"ref_48","first-page":"102551K","article-title":"Study on MMW radiation characteristics and imaging of stereoscopic metal targets","volume":"Volume 10255","author":"Liu","year":"2017","journal-title":"Selected Papers of the Chinese Society for Optical Engineering Conferences held October and November 2016"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"3745","DOI":"10.1109\/TGRS.2011.2159800","article-title":"Effects of a reflecting background on the results of active MMW SAR imaging of concealed objects","volume":"49","author":"Bertl","year":"2011","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., and Sheikh, Y. (2016, January 27\u201330). Convolutional Pose Machines. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Peng, C., Zhang, X., Yu, G., Luo, G., and Sun, J. (2017, January 21\u201326). Large Kernel Matters\u2014Improve Semantic Segmentation by Global Convolutional Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.189"},{"key":"ref_52","unstructured":"Hensman, P., and Masko, D. (2015). The Impact of Imbalanced Training Data for Convolutional Neural Networks. [Bachelor\u2019s Thesis, KTH Royal Institute of Technology]."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Pulgar, F.J., Rivera, A.J., Charte, F., and del jesus, M.J. (2017, January 21\u201323). On the impact of imbalanced data in convolutional neural networks performance. Proceedings of the International Conference on Hybrid Artificial Intelligence Systems Springer, La Rioja, Spain.","DOI":"10.1007\/978-3-319-59650-1_19"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/17\/4974\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:05:55Z","timestamp":1760177155000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/17\/4974"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,2]]},"references-count":53,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["s20174974"],"URL":"https:\/\/doi.org\/10.3390\/s20174974","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,2]]}}}