Advertisement

Segmentation of Concealed Objects in Passive Millimeter-Wave Images Based on the Gaussian Mixture Model

  • Wangyang Yu
  • Xiangguang Chen
  • Lei Wu
Article

Abstract

Passive millimeter wave (PMMW) imaging has become one of the most effective means to detect the objects concealed under clothing. Due to the limitations of the available hardware and the inherent physical properties of PMMW imaging systems, images often exhibit poor contrast and low signal-to-noise ratios. Thus, it is difficult to achieve ideal results by using a general segmentation algorithm. In this paper, an advanced Gaussian Mixture Model (GMM) algorithm for the segmentation of concealed objects in PMMW images is presented. Our work is concerned with the fact that the GMM is a parametric statistical model, which is often used to characterize the statistical behavior of images. Our approach is three-fold: First, we remove the noise from the image using both a notch reject filter and a total variation filter. Next, we use an adaptive parameter initialization GMM algorithm (APIGMM) for simulating the histogram of images. The APIGMM provides an initial number of Gaussian components and start with more appropriate parameter. Bayesian decision is employed to separate the pixels of concealed objects from other areas. At last, the confidence interval (CI) method, alongside local gradient information, is used to extract the concealed objects. The proposed hybrid segmentation approach detects the concealed objects more accurately, even compared to two other state-of-the-art segmentation methods.

Keywords

Passive millimeter wave (PMMW) Gaussian mixture model (GMM) Adaptive parameter initialization Confidence interval (CI) Hybrid segmentation 

Notes

Acknowledgement

Scientific research in this paper was supported by the Postdoctoral Foundation of China (20100480208).

References

  1. 1.
    M.Rangwala, F.Wang, K.Sarabandi. Study of Millimeter-Wave Radar for Helicopter Assisted-Landing System. IEEE Antennas and Propagation Magazine, 50(2), 13-25(2008).Google Scholar
  2. 2.
    E.Heinz, T.May, D.Born, et al. Passive submillimeter-wave stand-off video camera for security applications. Journal of Infrared, Millimeter, and Terahertz Waves, 31(11), 1355-1369(2010).Google Scholar
  3. 3.
    G.S.Nusinovich, R.Pu, T.M.Antonsen Jr, et al. Development of THz-range gyrotrons for detection of concealed radioactive materials. Journal of Infrared, Millimeter, and Terahertz Waves, 32(3), 380-402(2011).Google Scholar
  4. 4.
    X.Shen, C.R.Dietlein, E.Grossman, et al. Detection and segmentation of concealed objects in terahertz images. IEEE Transactions on Image Processing, 17(12), 2465-2475(2008).Google Scholar
  5. 5.
    A.Luukanen, R.Appleby, M.Kemp, et al. Millimeter-Wave and Terahertz Imaging in Security Applications. Terahertz Spectroscopy and Imaging. Springer Berlin Heidelberg, 491-520(2013).Google Scholar
  6. 6.
    N.N.Wang, J.H.Qiu, W.B.Deng. Development status of millimeter wave imaging systems for concealed detection. Infrared Technology, 31(3), 129-135(2009).Google Scholar
  7. 7.
    E.Grossman, C.Dietlein, J.Ala-Laurinaho, et al. Passive terahertz camera for standoff security screening. Applied optics, 49(19), E106-E120(2010).Google Scholar
  8. 8.
    E.N.Grossman, C.R.Dietlein, J.E.Bjarnason, et al. Imaging with modular linear arrays of cryogenic Nb microbolometers. SPIE Defense and Security Symposium. International Society for Optics and Photonics, 694806-694806-10(2008).Google Scholar
  9. 9.
    J.Schlaerth, A.Vayonakis, P.Day, et al. A millimeter and submillimeter kinetic inductance detector camera. Journal of Low Temperature Physics, 151(3-4), 684-689(2008).Google Scholar
  10. 10.
    D.Becker, C.Gentry,P. Ade, et al. High-resolution passive video-rate imaging at 350 GHz. SPIE Defense, Security, and Sensing. International Society for Optics and Photonics, 802206-802206-9(2011).Google Scholar
  11. 11.
    B.Watson, N.Walker, W.Ribarsky, et al. Effects of variation in system responsiveness on user performance in virtual environments. Human Factors: The Journal of the Human Factors and Ergonomics Society, 40(3), 403-414(1998).Google Scholar
  12. 12.
    A.N.Pergande. History and challenges of passive millimeter wave imaging. International Society for Optics and Photonics, 890006-890006-5(2013).Google Scholar
  13. 13.
    D.M.Sheen, D.L.McMakin, H.D.Colins, et al. Concealed explosive detection on personnel using a wideband holographic millimeter-wave imaging system. Proc.SPIE 2755,503-513(1996).Google Scholar
  14. 14.
    R.Appleby, R.N.Anderton, S.Price, et al. Mechanically scanned real time passive millimeter-wave imaging at 94GHz.Proc.SPIE 5077, 1-6(2003).Google Scholar
  15. 15.
    Z.Xiao, J.Xu, S.Peng, et al. Super-resolution image restoration of a PMMW sensor based on POCS algorithm. 1st ISSAA, 680-683(2006).Google Scholar
  16. 16.
    W.Yu, X.Chen, S.Dong, et al. Study on Image Enhancement Algorithm Applied to Passive Millimeter-wave Imaging Based on Wavelet Transformation. IEEE International Conference on Electrical and Control Engineering (ICECE), 856-859(2011).Google Scholar
  17. 17.
    M.Fallahpour, M. T.Ghasr, J. T.Case, et al. A Wiener filter-based synthetic aperture radar algorithm for microwave imaging of targets in layered media. Materials Evaluation, 69(10), 1227-1237(2011).Google Scholar
  18. 18.
    Buades, B.Coll, J.M.Morel. A non-local algorithm for image denoising. 2005 I.E. Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 2(2), 60-65(2005).Google Scholar
  19. 19.
    L.I.Rudin, S.Osher, E.Fatemi. Nonlinear total variation based noise removal algorithms. Physica D: Nonlinear Phenomena, 60(1): 259-268(1992).Google Scholar
  20. 20.
    J.T.Xiong, S.Q.Sun, L.C.Li, et al. An adaptive bidirectional diffusion process for passive millimeter-wave image denoising and enhancement. Journal of Infrared and Millimeter Waves, 30(6): 556-560(2011).Google Scholar
  21. 21.
    S.Lee, R.Rao, M.A.Slamani, Noise reduction and object enhancement in passive millimeter wave concealed weapon detection. International Conference on Image Processing, 1, 509–512(2002).Google Scholar
  22. 22.
    L.C.Ramac, M.K.Uner, P.K.Varshney, et al. Morphological filters and wavelet based image fusion for concealed weapons detection. Proc. SPIE Int. Soc. Optical Engineering, 3376, 110–119(1998).Google Scholar
  23. 23.
    Y.Tian, Y.Chang, H.Fang, et al. A hybrid concealed object detection method for PMMW images. Eighth International Symposium on Multispectral Image Processing and Pattern Recognition. International Society for Optics and Photonics, 89180T-89180T-6(2013).Google Scholar
  24. 24.
    G.J.Tian, Y.Xia, Y.Zhang, et al. Hybrid genetic and variational expectation-maximization algorithm for Gaussian-mixture-model-based brain MR image segmentation. IEEE Transactions on Information Technology in Biomedicine, 15(3), 373-380(2011).Google Scholar
  25. 25.
    H.Mobahi, S.R.Rao, A.Y.Yang, et al. Segmentation of natural images by texture and boundary compression. International journal of computer vision, 95(1), 86-98(2011).Google Scholar
  26. 26.
    Z.Ji, Y.Xia, Q.Sun, et al. Fuzzy local Gaussian mixture model for brain MR image segmentation. IEEE Transactions on Information Technology in Biomedicine, 16(3), 339-347(2012).Google Scholar
  27. 27.
    S.Yeom, D.S.Lee, J.Y.Son, et al. Real time outdoor concealed object detection with passive millimeter wave imaging. Optics express, 19(3): 2530-2536(2011).Google Scholar
  28. 28.
    F.Pernkopf, D.Bouchaffra. Genetic-based EM algorithm for learning Gaussian mixture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), 1344-1348(2005).Google Scholar
  29. 29.
    Simões R, Mönninghoff C, Dlugaj M, et al. Automatic segmentation of cerebral white matter hyperintensities using only 3D FLAIR images. Magnetic resonance imaging, 31(7), 1182-1189(2013).Google Scholar
  30. 30.
    K.Kayabol, J.Zerubia. Unsupervised amplitude and texture classification of SAR images with multinomial latent model. IEEE Transactions on image processing, 22(2), 561-572(2013).Google Scholar
  31. 31.
    M.A.T.Figueiredo, A.K.Jain. Unsupervised learning of finite mixture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(3), 381-396(2002).Google Scholar
  32. 32.
    R.C.Gonzalez, R.E.Woods, S.L.Eddins. Digital Image Processing.(Public House of Electronics Industry, Beijing, 2008).Google Scholar
  33. 33.
    T. Goldstein, S. Osher. The split Bregman method for L1-regularized problems. SIAM Journal on Imaging Sciences, 2(2), 323-343(2009).Google Scholar
  34. 34.
    P.Getreuer. Rudin-Osher-Fatemi total variation denoising using split Bregman. Image Processing On Line, 2, 74-95(2012).Google Scholar
  35. 35.
    K. Kokkinakis, A.K. Nandi. Exponent parameter estimation for generalized Gaussian probability density functions with application to speech modeling, Signal Process, 85, 1852–1858(2005).Google Scholar
  36. 36.
    S.Icer. Automatic segmentation of corpus callosum using Gaussian mixture modeling and Fuzzy C means methods. Computer methods and programs in biomedicine, 112, 38-46(2013).Google Scholar
  37. 37.
    D.A.Reynolds, R.C.Rose. Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Transactions on Speech and Audio Processing, 3(1), 72-83(1995).Google Scholar
  38. 38.
    S.Gazor, W.Zhang. Speech enhancement employing Laplacian-Gaussian mixture. IEEE Transactions on Speech and Audio Processing, 13(5), 896-904(2005).Google Scholar
  39. 39.
    M.W.Mak, H.B.Yu. A study of voice activity detection techniques for NIST speaker recognition evaluations. Computer Speech & Language, 28(1), 295-313(2014).Google Scholar
  40. 40.
    W.C.Gregory, J.D.Edward. Gaussian mixture model for edge-enhanced images. Journal of Electronic Imaging, 13(4), 731-737(2004).Google Scholar
  41. 41.
    C.Turgay, T.Tardi. Automatic image equalization and contrast enhancement using Gaussian mixture modeling. IEEE Transactions on Image processing, 21(1),145-156(2012).Google Scholar
  42. 42.
    J.Y.Chen, J.Yu, Y.L.Zhang. Multivariate video analysis and Gaussian process regression model based soft sensor for online estimation. Computers and Chemical Engineering, 64, 13-23(2014).Google Scholar
  43. 43.
    B.Aiazzi, L.Alparone, S.Baronti, Estimation based on entropy matching for generalized Gaussian PDF modeling. IEEE Signal Processing Letters, 6 (6), 138–140(1999).Google Scholar
  44. 44.
    Y.Bazi, L.Bruzzone, F.Melgani. Image thresholding based on the EM algorithm and the generalized Gaussian distribution. Pattern Recognition, 40(2), 619-634(2007).Google Scholar
  45. 45.
    S.Y.S.Fan, Y.Lin. A fast estimation method for the generalized Gaussian mixture distribution on complex images. Computer Vision and Image Understanding, 113(7), 839-853(2009).Google Scholar
  46. 46.
    C.S.Wallace, D.M.Boulton. An information measure for classification. Computer Journal, 11(2), 185-194(1968).Google Scholar
  47. 47.
    R.A.B.axter, J.JOliver. Finding overlapping components with MML. Statistics and Computing, 10(1), 5-16(2000).Google Scholar
  48. 48.
    M.S.Allili, N.Bouguila, D.Ziou. Finite general Gaussian mixture modeling and application to image and video foreground segmentation. Journal of Electronic Imaging, 17(1), 013005-013005-13(2008).Google Scholar
  49. 49.
    F.N.Fritsch, R.E.Carlson. Monotone piecewise cubic interpolation. SIAM Journal on Numerical Analysis, 17(2), 238-246(1980).Google Scholar
  50. 50.
    S.H.Shang. Downscaling crop water sensitivity index using monotone piecewise cubic interpolation. Pedosphere, 23(5): 662-667(2013).Google Scholar
  51. 51.
    L.R.Rabiner, J.H.McClellan, T.W.Parks. FIR digital filter design techniques using weighted Chebyshev approximation. Proceedings of the IEEE, 63, 595-610(1975).Google Scholar
  52. 52.
    S.A.Khoubrouy, I.M.S.Panahi. Criteria for estimating an FIR filter for cancelling the feedback path signal in hearing aid system. Signal Processing, 100, 101-111(2014).Google Scholar
  53. 53.
    P.P.Vaidyanatha, T.Q.Nguyen. Eigenfilters: A new approach to least-squares FIR filter design and applications including Nyquist filters. IEEE Transactions on Circuits and Systems, 34(1),11-23(1987).Google Scholar
  54. 54.
    Dasgupta, A.E.Raftery. Detecting features in spatial point processes with clutter via model-based clustering. Journal of the American Statistical Association, 93(441), 294-302(1998).Google Scholar
  55. 55.
    L.Hertz, R.W.Schafer. Multilevel thresholding using edge matching. Computer Vision, Graphics, and Image Processing, 44(3), 279-295(1988).Google Scholar
  56. 56.
    J.Canny. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6,679-698(1986).Google Scholar
  57. 57.
    D.S.Lee, S.Yeom, J.YSon, et al. Automatic image segmentation for concealed object detection using the expectation-maximization algorithm. Optics express, 18(10), 10659-10667(2010).Google Scholar
  58. 58.
    L.Jin, M.Fu. Segmentation of infrared images based on improved FCM segmentation algorithm. IEEE 2011 International Conference on Electrical and Control Engineering (ICECE), 5440-5443(2011).Google Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Beijing Institute of TechnologySchool of Chemical Engineering and EnvironmentBeijingChina

Personalised recommendations