Submit Manuscript
Peer Review
Editor Work
- Home
-
Articles & Issues
-
Data
- Dataset of Radar Detecting Sea
- SAR Dataset
- SARGroundObjectsTypes
- SARMV3D
- 3DRIED
- UWB-HA4D
- LLS-LFMCWR
- FAIR-CSAR
- FUSAR
- MSAR
- SDD-SAR
- DatasetinthePaper
- SpaceborneSAR3Dimaging
- DatasetintheCompetition
- Sea-land Segmentation
- SAR-Airport
- Hilly and mountainous farmland time-series SAR and ground quadrat dataset
-
Report
-
Course
-
About
-
Publish
- Editorial Board
- Chinese
| Citation: | SHI Jun, QUE Yujia, ZHOU Zenan, et al. Near-field millimeter wave 3D imaging and object detection method[J]. Journal of Radars, 2019, 8(5): 578–588. doi: 10.12000/JR18089
|
Near-field Millimeter Wave 3D Imaging and Object Detection Method
DOI: 10.12000/JR18089
More Information-
Abstract
Active mm-wave linear-array 3D imaging system has become one of the active research areas in the field of imaging for human security. In this paper, the operating mode, signal model, and imaging algorithm are introduced. Deep learning algorithms, including the Convolutional Neural Network (CNN) with heat map and You Only Look Once (YOLO) network, were used for the object detection of human security image. The results show that the method based on heat map and YOLO can both detect foreign objects. We find that the CNN with heat map has a simple network construction and can be easily trained, but the detection process needs to traverse the whole image, which is relatively time-consuming, and the size of the detection region cannot adapt to the objects. On the contrary, though with a relatively complex construction, YOLO network has advantages in terms of detection efficiency and accuracy. Furthermore, the size of the detection region can adapt to the objects, which is more suitable for the human security imaging application. -
References
[1] CURRIE N C, DEMMA F J, FERRIS D D JR, et al. ARPA/NIJ/Rome laboratory concealed weapon detection program: An overview[C]. Proceedings of SPIE 2755, Signal Processing, Sensor Fusion, and Target Recognition V, Orlando, USA, 1996: 492–502.[2] FARHAT N H and GUARD W R. Millimeter wave holographic imaging of concealed weapons[J]. Proceedings of the IEEE, 1971, 59(9): 1383–1384. doi: 10.1109/PROC.1971.8441[3] GONZALEZ-VALDES B, ALLAN G, RODRIGUEZ-VAQUEIRO Y, et al. Sparse array optimization using simulated annealing and compressed sensing for near-field millimeter wave imaging[J]. IEEE Transactions on Antennas and Propagation, 2014, 62(4): 1716–1722. doi: 10.1109/TAP.2013.2290801[4] 成彬彬, 李慧萍, 安健飞, 等. 太赫兹成像技术在站开式安检中的应用[J]. 太赫兹科学与电子信息学报, 2015, 13(6): 843–848. doi: 10.11805/TKYDA201506.0843CHENG Binbin, LI Huiping, AN Jianfei, et al. Application of terahertz imaging in standoff security inspection[J]. Journal of Terahertz Science and Electronic Information Technology, 2015, 13(6): 843–848. doi: 10.11805/TKYDA201506.0843[5] 温鑫, 黄培康, 年丰, 等. 主动式毫米波近距离圆柱扫描三维成像系统[J]. 系统工程与电子技术, 2014, 36(6): 1044–1049. doi: 10.3969/j.issn.1001-506X.2014.06.05WEN Xin, HUANG Peikang, NIAN Feng, et al. Active millimeter-wave near-field cylindrical scanning three-dimensional imaging system[J]. Systems Engineering and Electronics, 2014, 36(6): 1044–1049. doi: 10.3969/j.issn.1001-506X.2014.06.05[6] APPLEBY R and WALLACE H B. Standoff detection of weapons and contraband in the 100 GHz to 1 THz region[J]. IEEE Transactions on Antennas and Propagation, 2007, 55(11): 2944–2956. doi: 10.1109/TAP.2007.908543[7] DALAL N and TRIGGS B. Histograms of oriented gradients for human detection[C]. Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005: 886–893.[8] AHONEN T, HADID A, and PIETIKAINEN M. Face description with local binary patterns: Application to face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12): 2037–2041. doi: 10.1109/TPAMI.2006.244[9] VIOLA P and JONES M. Rapid object detection using a boosted cascade of simple features[C]. Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, USA, 2001: I-511–I-518. doi: 10.1109/CVPR.2001.990517.[10] Kelly E J. An adaptive detection algorithm[J]. IEEE Transactions on Aerospace and Electronic Systems, 1986, AES-22(2): 115–127. doi: 10.1109/TAES.1986.310745[11] KRIZHEVSKY A, SUTSKEVER I, and HINTON G E. Imagenet classification with deep convolutional neural networks[C]. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, USA, 2012: 1097–1105.[12] SIMONYAN K and ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv: 1409.1556, 2014.[13] GIRSHICK R. Fast R-CNN[C]. Proceedings of 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1440–1448.[14] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, 2015: 91–99.[15] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 580–587.[16] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 779–788.[17] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]. Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 2016: 21–37.[18] GOMEZ-MAQUEDA I, ALMOROX-GONZALEZ P, CALLEJERO-ANDRES C, et al. A millimeter-wave imager using an illuminating source[J]. IEEE Microwave Magazine, 2013, 14(4): 132–138. doi: 10.1109/MMM.2013.2248652[19] 师君. 双基地SAR与线阵SAR原理及成像技术研究[D]. [博士论文], 电子科技大学, 2009.SHI Jun. Research on principles and imaging techniques of bistatic SAR & LASAR[D]. [Ph.D. dissertation], University of Electronic Science and Technology of China, 2009.[20] ROTHE R, GUILLAUMIN M, and VAN GOOL L. Non-maximum suppression for object detection by passing messages between windows[C]. Proceedings of the 12th Asian Conference on Computer Vision, Singapore, 2014: 290–306. Relative Articles
Cited by
Periodical cited type(6)
1. 王纪平，刘衍琦，邓钱钰，郭淑婷，毛新华. 基于PAST的毫米波雷达MIMO阵列幅相误差校正算法. 信号处理. 2024(09): 1633-1647 . 
2. 宁宝俊. 毫米波雷达在斜拉桥索力监测中的应用. 西部交通科技. 2024(07): 157-160 . 3. 张春杰，陈奇，赵佳琦. 基于注意力机制CNN-LSTM的毫米波雷达点云特征数据预测生成. 电讯技术. 2024(11): 1718-1725 . 4. 耿同乐. 电流反馈在毫米波雷达信号处理中的应用. 集成电路应用. 2024(11): 26-27 . 5. 于丹阳，杜磊. 一种基于快速迭代自适应算法的毫米波雷达波达角高精度测量方法. 计量科学与技术. 2024(11): 3-9+21 . 6. 孙航，张路，季国田. 智能网联汽车标准体系及重点标准研究与展望. 汽车安全与节能学报. 2024(06): 795-812 . Other cited types(29)
-
Proportional views
- Publishing Ethics
- Journal Insights
- Abstracting & Indexing
- Peer Review Policies
- Guide for Authors
- Conference
- ISSN 2095-283X (Print)ISSN 2097-339X (Online)
- CN 10-1030/TN
- CODEN LXEUAO
About Journal
- Sponsor: China Radio Detection and Ranging Industry Association (CRIA)
- Phone: 010-58887062
- Email：radars@aircas.ac.cn
- Publisher: Leida Xuebao Bianjibu (Editorial office of the Journal of Radars)
Contacts Us
京ICP备20021838号-8
Supported by: Beijing Renhe Information Technology Co. Ltd
Export File
Citation
Yang Jin-long, Liu Feng-mei, Wang Dong, Ge Hong-wei. Affinity Propagation Based Measurement Partition Algorithm for Multiple Extended Target Tracking[J]. Journal of Radars, 2015, 4(4): 452-459. doi: 10.12000/JR15003
Format
Content
DownLoad:
- Figure 1. The geometric model of near field millimeter wave 3D imaging
- Figure 2. The 2D imaging result
- Figure 3. The CNN structure
- Figure 4. The target detection structure based on heat map
- Figure 5. The training process of YOLO
- Figure 6. Removal of repeated prediction box by NMS algorithms
- Figure 7. The original measured image
- Figure 8. The image after processing
- Figure 9. Samples of training classification network
- Figure 10. The average loss and accuracy in classification network training
- Figure 11. The average loss in YOLO network training
- Figure 12. YOLO network detection results of different image size
- Figure 13. YOLO test results (different training numbers)
- Figure 14. Test results based on heat map and YOLO