Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network
Abstract
:1. Introduction
2. Dataset
2.1. Imaging Description
2.2. Terahertz Human Dataset
2.3. Terahertz Classification Dataset
3. Proposed Method
3.1. Terahertz Classification Model
3.1.1. Architecture of CNN
Algorithm 1. Stochastic gradient descent (SGD) with momentum. |
Require: Initial parameter , initial velocity . |
Require: Learning rate , momentum parameter . |
while do stopping criterion not met do |
Sample a minibatch of images from the training set with corresponding label |
Compute gradient estimate: |
Compute velocity update: |
Apply update: |
end while |
3.1.2. Transfer Learning
3.1.3. Experiment Analysis
3.2. Terahertz Image Detection
3.2.1. Threshold Segmentation
3.2.2. The Improved Faster R-CNN
3.2.3. Experimental Analysis
4. Discussion
5. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Siegel, P.H. Terahertz technology. IEEE Trans. Microw. Theory Tech. 2002, 50, 910–928. [Google Scholar] [CrossRef]
- Mittleman, D. Sensing with Terahertz Radiation; Springer: Berlin, Germany, 2003; pp. 301–340. [Google Scholar]
- McMakin, D.L.; Sheen, D.M.; Collins, H.D.; Hall, T.E.; Severtsen, R.H. Wideband millimeter-wave holographic weapons surveillance systems. In Proceedings of the European Symposium on Optics for Environmental and Public Safety, Munich, Germany, 15 September 1995; pp. 131–141. [Google Scholar]
- Drolet, G. Contraband detection program. In Proceedings of the Chemistry and Biology-Based Technologies for Contraband Detection, Boston, MA, USA, 17 February 1997; pp. 162–172. [Google Scholar]
- Coutu, R.A.; Medvedev, I.R.; Petkie, D.T. Improved Sensitivity MEMS Cantilever Sensor for Terahertz Photoacoustic Spectroscopy. Sensors 2016, 16, 251. [Google Scholar] [CrossRef] [PubMed]
- Sheen, D.M.; McMakin, D.L.; Hall, T.E. Three-dimensional millimeter-wave imaging for concealed weapon detection. IEEE Trans. Microw. Theory Tech. 2001, 49, 1581–1592. [Google Scholar] [CrossRef]
- Jing, G.B.; Sun, G.C.; Xia, X.G.; Xing, M.D.; Bao, Z. A novel two-step approach of error estimation for stepped-frequency mimo-sar. IEEE Geosci. Remote Sens. Lett. 2017, 14, 2290–2294. [Google Scholar] [CrossRef]
- Chen, J.; Sun, G.C.; Wang, Y.; Guo, L.; Xing, M.; Gao, Y. An analytical resolution evaluation approach for bistatic geosar based on local feature of ambiguity function. IEEE Trans. Geosci. Remote Sens. 2017, 56, 2159–2169. [Google Scholar] [CrossRef]
- Evans, D.L.; Plaut, J.J.; Stofan, E.R. Overview of the spaceborne imaging radar-c/x-band synthetic aperture radar (sir-c/x-sar) missions. Remote Sens. Environ. 1996, 59, 135–140. [Google Scholar] [CrossRef]
- Chen, J.; Sun, G.C.; Xing, M.; Yang, J.; Ni, C.; Zhu, Y.; Shu, W.; Liu, W. A parameter optimization model for geosynchronous sar sensor in aspects of signal bandwidth and integration time. IEEE Geosci. Remote Sens. Lett. 2016, 13, 1374–1378. [Google Scholar] [CrossRef]
- Rohling, H. Radar cfar thresholding in clutter and multiple target situations. IEEE Trans. Aerosp. Electron. Syst. 1983, AES-19, 608–621. [Google Scholar] [CrossRef]
- Cattermole, K.W. The fourier transform and its applications. Electron. Power 1986, 11, 357. [Google Scholar] [CrossRef]
- Nitzberg, R. Constant-false-alarm-rate signal processors for several types of interference. IEEE Trans. Aerosp. Electron. Syst. 1972, AES-8, 27–34. [Google Scholar] [CrossRef]
- Fogel, I.; Sagi, D. Gabor filters as texture discriminator. Biol. Cybern. 1989, 61, 103–113. [Google Scholar] [CrossRef]
- Meyer, Y. Wavelets and operators. Differ. Perspect. Wavel. 1993, 47, 35–58. [Google Scholar]
- Charnes, A.; Frome, E.L.; Yu, P.L. The equivalence of generalized least squares and maximum likelihood estimates in the exponential family. J. Am. Stat. Assoc. 1976, 71, 169–171. [Google Scholar] [CrossRef]
- Haralick, R.M.; Shanmugam, K.; Dinstein, I.H. Textural features for image classification. IEEE Trans. Syst. Man Cybern. Part B Cybern. 1973, SMC-3, 610–621. [Google Scholar] [CrossRef]
- McCaleb, M.R. A conceptual data model of datum systems. J. Res. Nat. Inst. Stand. Technol. 1999, 104, 349–400. [Google Scholar] [CrossRef]
- LOEW. Object recognition from local scale-invariant features. In Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, 20–27 September 1999. [Google Scholar]
- Lowe, D.G. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 2004, 60, 91–110. [Google Scholar] [CrossRef]
- Lindeberg, T. Scale selection. In Computer Vision: A Reference Guide; Ikeuchi, K., Ed.; Springer: Boston, MA, USA, 2014; pp. 701–713. [Google Scholar]
- Krystian, M.; Cordelia, S. Performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 2005, 27, 1615–1630. [Google Scholar]
- Ning, Q.; Sejnowski, T.J. Predicting the secondary structure of globular proteins using neural network models. J. Mol. Biol. 1988, 202, 865–884. [Google Scholar]
- Ordóñez, F.J.; Roggen, D. Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors 2016, 16, 115. [Google Scholar] [CrossRef] [PubMed]
- Weng, J.; Ahuja, N.; Huang, T.S. Cresceptron: A self-organizing neural network which grows adaptively. In Proceedings of the International Joint Conference on Neural Networks, Baltimore, MD, USA, 7–11 June 1992; pp. 576–581. [Google Scholar]
- Lecun, Y.; Boser, B.; Denker, J.S.; Henderson, D.; Howard, R.E.; Hubbard, W.; Jackel, L.D. Backpropagation applied to handwritten zip code recognition. In Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada, 14–16 August 1995; pp. 541–551. [Google Scholar]
- Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar] [CrossRef] [Green Version]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. Imagenet classification with deep convolutional neural networks. Commun. ACM 2017, 60, 84–90. [Google Scholar] [CrossRef]
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Pan, S.J.; Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 2010, 22, 1345–1359. [Google Scholar] [CrossRef]
- Girshick, R.; Donahue, J.; Darrell, T.; Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 2014, 37, 1904–1916. [Google Scholar] [CrossRef] [PubMed]
- Ren, S.; He, K.; Girshick, R.; Sun, J. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 2015, 39, 1137–1149. [Google Scholar] [CrossRef] [PubMed]
- Redmon, J.; Divvala, S.; Girshick, R.; Farhadi, A. You only look once: Unified, real-time object detection. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.Y.; Berg, A.C. SSD: Single Shot MultiBox Detector. In Computer Vision—ECCV 2016. ECCV 2016. Lecture Notes in Computer Science; Leibe, B., Matas, J., Sebe, N., Welling, M., Eds.; Springer: Berlin, Germany, 2016; Volume 9905. [Google Scholar]
- Dai, J.; Li, Y.; He, K.; Sun, J. R-FCN: Object detection via region-based fully convolutional networks. In Proceedings of the Neural Information Processing Systems, Barcelona, Spain, 5–10 December 2016. [Google Scholar]
- Everingham, M.; Eslami, S.M.A.; Gool, L.V.; Williams, C.K.I.; Winn, J.; Zisserman, A. The pascal visual object classes challenge: A retrospective. Int. J. Comput. Vis. 2009, 88, 303–338. [Google Scholar] [CrossRef]
- Lin, T.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollár, P.; Zitnick, C.L. Microsoft COCO: Common Objects in Context. In Computer Vision—ECCV 2014. ECCV 2014. Lecture Notes in Computer Science; Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T., Eds.; Springer: Berlin, Germany, 2014; Volume 8693. [Google Scholar]
- Rumelhart, D.E.; Hinton, G.E.; Williams, R.J. Learning representations by back-propagating errors. Read. Cognit. Sci. 1986, 323, 399–421. [Google Scholar] [CrossRef]
- Li, F.F.; Fergus, R.; Perona, P. Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop, Washington, DC, USA, 27 June–2 July 2004. [Google Scholar]
Type | Quantity | Scale |
---|---|---|
person | 26,505 | [25, 289, 28, 363] |
knife | 4494 | [3, 129, 8, 113] |
handgun | 2591 | [10, 67,1, 63] |
bottle | 1747 | [9, 60, 16, 83] |
phone | 1190 | [8, 48, 11, 84] |
Random Initialization | Fine-Tuning Output | Fine-Tuning fc7 | Fine-Tuning fc6 | |
---|---|---|---|---|
convolutional-layers | 1.0 | 1.0 | 1.0 | 1.0 |
fc6 layer | 1.0 | 1.0 | 1.0 | 10 |
fc7 layer | 1.0 | 1.0 | 10 | 10 |
softmax-layer | 1.0 | 10 | 10 | 10 |
Strategy | Random Initialization | Fine-Tuning Output | Fine-Tuning fc7 | Fine-Tuning fc6 |
---|---|---|---|---|
accuracy | 95.98% | 96.68% | 96.98% | 96.75% |
YOLOv2 | SSD | R-FCN | FRCNN | IFRCNN | |
---|---|---|---|---|---|
person | 85.34 | 90.78 | 91.06 | 90.43 | 98.75 |
knife | 67.90 | 81.08 | 83.71 | 80.36 | 85.44 |
handgun | 67.45 | 69.21 | 68.18 | 67.32 | 70.06 |
bottle | 30.28 | 44.64 | 42.46 | 38.89 | 46.72 |
phone | 34.84 | 45.05 | 46.47 | 45.53 | 47.18 |
mAP | 57.16 | 66.15 | 66.38 | 64.51 | 69.70 |
Missing Alarm | False Alarm | |
---|---|---|
person | 1.25% | 3.47% |
knife | 10.14% | 18.53% |
handgun | 30.32% | 8.06% |
bottle | 58.02% | 15.73% |
phone | 48.17% | 20.90% |
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, J.; Xing, W.; Xing, M.; Sun, G. Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network. Sensors 2018, 18, 2327. https://doi.org/10.3390/s18072327
Zhang J, Xing W, Xing M, Sun G. Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network. Sensors. 2018; 18(7):2327. https://doi.org/10.3390/s18072327
Chicago/Turabian StyleZhang, Jinsong, Wenjie Xing, Mengdao Xing, and Guangcai Sun. 2018. "Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network" Sensors 18, no. 7: 2327. https://doi.org/10.3390/s18072327
APA StyleZhang, J., Xing, W., Xing, M., & Sun, G. (2018). Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network. Sensors, 18(7), 2327. https://doi.org/10.3390/s18072327