Video Image Recognition and Early Warning Algorithm of Public Security Prevention and Control Based on Deep Learning

  • Qing Lu
  • Xuchong LiuEmail author
  • Zhaohui Jiang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 551)


As we all know, video surveillance plays an increasingly important role in the prevention and treatment of major public security cases (departments) and the maintenance of public security and other social security prevention and control work. At present, the research on public security prevention and control in the environment is still relatively backward. Because there are many cameras and large amount of image data, it is difficult to automatically identify image data. Based on the above reasons, this paper uses deep learning method to identify and warn video images to achieve automatic recognition. The goal of the research method of this paper is to combine the mathematical analysis of the existing deep learning model and summarize the characteristics of the deep learning method in the theoretical model. A character image recognition algorithm based on extended nonlinear kernel residual network is proposed. An image retrieval algorithm based on extended nonlinear kernel residual network and hash is proposed.


Public security prevention and control Image identification Deep learning Feature extraction Search image Extended nonlinear kernel residual network 



This research was supported by Innovative Project of Science and Technology Planning Application of Ministry of Public Security (2018YYCXHNST048), Scientific Research Excellent Youth Project of Hunan Education Department (18B549), Science and Technology Project of Hunan Public Security Department, Hunan Natural Science Foundation (2018J2108), Hunan Social Science Foundation (17YBA151), Hunan Education Department Innovation Platform Open Fund (15K037), The Science and Technology Project of Hunan Province of China under Grant (2017SK1040).


  1. 1.
    Huang, T.: Research on security threats and countermeasures in the “Internet+” environment. Net Monthly J. (02), 110–118 (2018)Google Scholar
  2. 2.
    Wang, H., Cui, B.: Study on the construction of social security prevention and control system from the perspective of the integration of risk society and information society. J. Hebei Public Secur. Police Vocat. Coll. 18(04), 32–34 (2018)Google Scholar
  3. 3.
    Li, Y., Song, T., Shen, Y.: Application research of community security prevention and control in the background of informationization. Digit. Commun. World (11), 28–29 (2018)Google Scholar
  4. 4.
    Jin, W.: A sleek project integration solution that can be seen, prevented and controlled. China Public Saf. 12, 125–126 (2018)Google Scholar
  5. 5.
    Li, T.: Application of big data in public security prevention and control. Zhengzhou University (2018)Google Scholar
  6. 6.
    Hou, L.: Analysis of the prevention and control of social security accuracy in the background of big data. Law Soc. (33), 130–131 (2018)Google Scholar
  7. 7.
    Li, H.: Research on the prevention and control management of public security in Lanzhou under the background of big data. Lanzhou University (2018)Google Scholar
  8. 8.
    Dai, J., Liu, Z.: A review of research on image recognition algorithm based on deep learning. Comput. Prod. Circ. (03), 188 (2018)Google Scholar
  9. 9.
    Chen, B.: Image recognition algorithm based on feature coding and deep learning. South China University of Technology (2018)Google Scholar
  10. 10.
    Rao, Z.: Research on character image recognition and image retrieval based on deep learning. Hubei University of Technology (2018)Google Scholar
  11. 11.
    Wang, L., Zhong, Y., Li, Z., He, Y.: On-line detection algorithm for fabric defects based on deep learning. Comput. Appl. 1–6 (2019)Google Scholar
  12. 12.
    Yin, T., Zeng, X.: Design and analysis of library collection resources recommendation model from the perspective of deep learning. Mod. Intell. (04), 103–107, 124 (2019)Google Scholar
  13. 13.
    Rao, Z., Zeng, C., Wu, M., et al.: Research on a handwritten character recognition algorithm based on an extended nonlinear kernel residual network. KSII Trans. Internet Inf. Syst. 12(1), 413–435 (2018)Google Scholar
  14. 14.
    Liu, H., Wang, R., Shan, S., et al.: Deep supervised hashing for fast image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2064–2072 (2016)Google Scholar
  15. 15.
    Shen, J., Chi, M.: Application of deep prior image features in urban remote sensing big data. Comput. Syst. 27(09), 33–39 (2018)Google Scholar
  16. 16.
    Yang, Y.: Research and application of binary descriptor based on deep learning. Chengdu University of Information Science and Technology (2018)Google Scholar
  17. 17.
    Zhong, F., Huang, S., Zhang, X., Huang, Y., Zhang, W., Li, S.: Image preprocessing and feature extraction of typical defects of GIS switch based on X-ray imaging technology. Autom. Instrum. (05), 162–166, 170 (2018)Google Scholar
  18. 18.
    Chen, G.: Design and implementation of content-based image retrieval system. Nanjing University (2018)Google Scholar
  19. 19.
    Singh, A., Dutta, M.K., Jennane, R., Lespessailles, E.: Classification of the trabecular bone structure of osteoporotic patients using machine vision. Comput. Biol. Med. 91, 148–158 (2017)CrossRefGoogle Scholar
  20. 20.
    Jiao, J., Wang, X., Deng, Z.: Build a robust learning feature descriptor by using a new image visualization method for indoor scenario recognition. Sensors (Basel Switz.) 17(7), 1569 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Hunan Police AcademyChangshaChina
  2. 2.Hunan Provincial Key Laboratory of Network Investigational TechnologyHunanChina
  3. 3.Public Security Department of Hunan ProvinceHunanChina

Personalised recommendations