Optical Review

, Volume 24, Issue 3, pp 416–427 | Cite as

Noise reduction for lidar returns using self-adaptive wavelet neural network

Regular Paper

Abstract

Lidar has been widely applied in many fields, such as meteorology and environment. However, because lidar returns are very weak, the influence of noise on useful signal is very serious. To obtain useful lidar return signals from raw data, a self-adaptive method combining wavelet analysis and a neural network that suppresses noise is proposed, in which the orthogonal Daubechies wavelet family serves as node functions in the hidden layer of the neural network, a search algorithm is selected to optimize the parameters and thresholds, and the Levenberg–Marquardt algorithm is adopted in the neural network gradient algorithm. Some comparative experiments were carried out to verify the feasibility of the noise reduction method and the results showed that the signal-to-noise ratio (SNR) of the common wavelet threshold denoising method is about 10, while that of the self-adaptive wavelet neural network denoising method is more than 20. From the experimental results, it can be seen that the wavelet neural network denoising method has less distortion and a higher SNR value than other methods, giving it superior performance.

Keywords

Signal processing Lidar Wavelet neural network Denoising 

Notes

Acknowledgements

This work was supported by the National Natural Science Foundation of China (NSFC) (Grant Nos. 61565001, 61168004, and 61450007), the Leading Talents of Scientific and Technological Innovation of Ningxia, the West Light Talent Plan of the Chinese Academy of Sciences, the Key Scientific Research Project of Beifang University of Nationalities (Grant No. 2015KJ02), and the Scientific Research Project of Beifang University of Nationalities (Grant No. 2016GQR07).

References

  1. 1.
    Haibin, Z., Guang, Y., Maoren, J.: The method of lidar-return signal analysis and processing. Sci. Technol. Inf. 11, 27–29 (2009)Google Scholar
  2. 2.
    Wei, H.: Study of the method of lidar-return signal processing and detection, pp. 1–9. University of Electronic Science and Technology of China, Chengdu (2003)Google Scholar
  3. 3.
    Zengdong, L., Jianguo, L., Yihuai, L., et al.: Noise reduction in lidar signal based on EMD. Opto-Electronic Eng. 35, 79–83 (2008)Google Scholar
  4. 4.
    Awei, Z.: Study of Mie lidar signal processing and visualization technology, pp. 3–4. Xi’an University of Technology, Xi’an (2008)Google Scholar
  5. 5.
    Xiwen, Q., Hui, Z., Qinfen, T., et al.: Atmospheric attenuation effect of lidar signal. J. Appl. Opt. 21, 21–25 (2000)Google Scholar
  6. 6.
    Songhua, W., Liu, Z., Liu, B.: Enhancement of lidar backscatters signal-to-noise ratio using empirical mode decomposition method. Opt. Comm. 267(1), 137–144 (2006)ADSCrossRefGoogle Scholar
  7. 7.
    Wen, L., Zhengshi, L., Yunjian, G.: Several methods of wavelet denoising. J. Hefei Univ. Technol. 25(2), 167–172 (2002)Google Scholar
  8. 8.
    Jiandong, M., Dengxin, H., Yuefeng, W., et al.: Noise reduction in lidar based on wavelet packet analysis. China J. Lasers 02, 226–233 (2011)Google Scholar
  9. 9.
    Nian, C., Kuanggu, H., Fangzhen, L., et al.: Noise reduction in image based on wavelet neural network. Acta Biophys. Sin. 1, 78–82 (2005)Google Scholar
  10. 10.
    Shouping, C., Rui, D., Xiaoli, L.: Analysis of 30 cases of neural network in MATLAB, pp. 208–217. Beihang University, Beijing (2010)Google Scholar
  11. 11.
    Ze, C., Tianjin, F., Gang, C.: A kind of wavelet neural network based on BP algorithm. J. Ocean Univ. Qingdao 1, 122–128 (2001)Google Scholar
  12. 12.
    Klett, J.D.: Stable analytical inversion solution for processing lidar returns. Appl. Opt. 20(2), 211–220 (1981)ADSCrossRefGoogle Scholar
  13. 13.
    Renhou, L.: The theory and method of intelligent control (Second edition), pp. 233–241. Xi’an Science and Technology Press, Xi’an (2013)Google Scholar
  14. 14.
    Xipeng, Y., Yangyu, F., Zeming, D., et al.: Noise reduction of terpedo ultrasonic fuze signal processing based on self-adapted wavelet neural network. Terpedo Technol. 17, 19–22 (2009)Google Scholar
  15. 15.
    Mingcai, L.: Wavelet analysis and its applications (Second edition), pp. 10–11. Tsinghua University, Beijing (2005)Google Scholar
  16. 16.
    Zhiqing, D.: Fredholm integral equation of wavelet method, pp. 20–25. Xi’an University of Architecture and Technology, Xi’an (2009)Google Scholar
  17. 17.
    Changyou, W.: The study and applications of neural networks, pp. 17–21. Northeast Agricultural University, Harbin (2007)Google Scholar
  18. 18.
    Jiang, Z., Gao, W.: Wavelet neutral network for function learning. IEEE Trans. Signal Process. 43(6), 1485–1497 (1995)ADSCrossRefGoogle Scholar
  19. 19.
    Liang Y.: Integral equation of wavelet method, p. 23. Xi’an University of Architecture and Technology, Xi’an (2008)Google Scholar
  20. 20.
    Fatai, Z., Dengxin, H., Awei, Z.: Empirical mode decomposition algorithm research & application of Mie lidar atmospheric backscattering signal. Chinese J. Lasers 36(5), 1068–1074 (2009)CrossRefGoogle Scholar
  21. 21.
    Fernald, F. G.: Analysis of atmospheric lidar observation: some comments. Appl. Opt. 23(5), 652–653 (1984)ADSCrossRefGoogle Scholar
  22. 22.
    Collis, R.T.H.: Lidar: a new atmosphere probe. Q. J. R. Meteorol. Soc. 92(392), 220–230 (1966)ADSCrossRefGoogle Scholar

Copyright information

© The Optical Society of Japan 2017

Authors and Affiliations

  1. 1.School of Electrical and Information EngineeringBeifang University of NationalitiesYinchuanChina

Personalised recommendations