Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Textural feature extraction based on time–frequency spectrograms of humans and vehicles

© The Institution of Engineering and Technology
Received 10/10/2014, Accepted 11/05/2015, Revised 04/05/2015, Published 01/12/2015

Extraction of features and subsequent classification of ground moving targets, especially humans and vehicles, are topics of great relevance for the theoretical research and practical application in the signal processing of the ground surveillance radar. Through the time–frequency analysis of ground moving target, the energy distribution of spectrogram can be regarded as a kind of image texture. On the basis of this, a novel method for the feature extraction of micro-motion targets is proposed in this study. In the proposed method, the spectrograms of targets’ echoes are first obtained through the short-time Fourier transform. To improve the precision of features extracted, a pre-processing based on the spectrogram is followed to enhance image features. On the basis of targets’ spectrograms, the entropy, third-order moment of statistical histogram and directionality features are extracted finally as jointly effective features of micro-motion targets. The support vector machine (SVM) is utilised to classify the ground moving targets and a high probability of correct classification is obtained. The experimental results under different signal-to-noise ratio and training sample number conditions verify the validity and robustness of the proposed method.

Inspec keywords: statistical analysis; Fourier transforms; image texture; support vector machines; radar imaging; video surveillance; feature extraction

Other keywords: signal processing; time frequency spectrograms; micromotion targets; short-time Fourier transform; time frequency analysis; textural feature extraction; image texture; ground moving target; ground surveillance radar; energy distribution; subsequent classification; support vector machine; statistical histogram; SVM; ground moving targets

Subjects: Computer vision and image processing techniques; Knowledge engineering techniques; Other topics in statistics; Optical, image and video signal processing; Radar equipment, systems and applications; Other topics in statistics; Integral transforms; Video signal processing; Integral transforms; Television and video equipment, systems and applications

References

    1. 1)
      • 19. Ram, S.S., Ling, H.: ‘Simulation of human micro-Dopplers using computer animation data’. IEEE Radar Conf., Rome, 2008, pp. 1–6.
    2. 2)
      • 20. Kim, Y., Ling, H.: ‘Human activity classification based on micro-Doppler signatures using an artificial neural network’. Antennas and Propagation Society Int. Symp., 2008, pp. 1–4.
    3. 3)
    4. 4)
    5. 5)
    6. 6)
    7. 7)
    8. 8)
    9. 9)
    10. 10)
      • 33. Gonzalez, R.C., Woods, R.E.: ‘Digital image processing’ (Prentice-Hall, Englewood Cliffs, NJ, 2002, 2nd edn.).
    11. 11)
    12. 12)
      • 27. Stanković, L., Daković, M., Thayaparan, T.: ‘Time–frequency signal analysis with applications’ (Artech House Inc., Norwood, MA, 2013).
    13. 13)
      • 18. Bürkan, T., Sevgi, Z.G., Melda, Y., Ali, C.G.: ‘Classification of human micro-Doppler in radar network’. 2013 IEEE Radar Conf., Ottawa, ON, 2013, pp. 1–6.
    14. 14)
    15. 15)
      • 25. Materka, A., Strzelecki, M.: ‘Texture analysis methods – a review’. Technical Report, Institute of Electronics, Technical University of Lodz, Brussels, 1998.
    16. 16)
    17. 17)
    18. 18)
    19. 19)
    20. 20)
    21. 21)
    22. 22)
      • 13. Thayaparan, T., Abrol, S., Riseborough, E., Stankovic, L., Lamothe, D., Duff, G.: ‘Analysis of radar micro-Doppler signatures from experimental helicopter and human data’, IET Proc. Radar Sonar Navig., 2007, 1, (4), pp. 288–299.
    23. 23)
    24. 24)
      • 6. Li, K.M., Zhang, Q.: ‘A novel method for occlusion modeling and micro-Doppler analysis of truck target’. IET Int. Radar Conf., Xi'an, 2013, pp. 1–5.
    25. 25)
    26. 26)
    27. 27)
      • 32. Guan, W.S., Hao, Y.L., Lu, Z.Z., Wu, P.: ‘The research of satellite cloud image recognition base on variational method and texture feature analysis’. The Second IEEE Conf. on Industrial Electronics and Applications, Harbin, 2007, pp. 2816–2820.
    28. 28)
    29. 29)
    30. 30)
    31. 31)
      • 34. Islam, M.M., Zhang, D.S., Lu, G.J.: ‘A geometric method to compute directionality features for texture images’ (Multimedia and Expo, Hannover, 2008), pp. 1521–1524.
    32. 32)
      • 24. Roslan, R., Jamil, N.: ‘Texture feature extraction using 2-D Gabor filters’. 2012 Int. Symp. on Computer Applications and Industrial Electronics (ISCAIE2012), Kota Kinabalu, Malaysia, 2012, pp. 173–178.
    33. 33)
      • 11. Tran, H.T., Melino, R., Berry, P.E., Yau, D.: ‘Microwave radar imaging of rotating blades’. Int. Conf. on Radar, Adelaide, SA, 2013, pp. 202–207.
    34. 34)
      • 26. Jian, M.W., Dong, J.Y., Gao, D.W., Liang, Z.J.: ‘New texture features based on wavelet transform coinciding with human visual perception’. ACIS Eighth Int. Conf. on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, Qingdao, 2007, pp. 369–373.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-rsn.2014.0432
Loading

Related content

content/journals/10.1049/iet-rsn.2014.0432
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address