Advertisement

Real-Time Human Body Detection Based on YOLOv2 Network

  • Xiaopeng Liu
  • Yan Liu
  • Hong Wang
  • Jiangyun LiEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 582)

Abstract

It is a pivotal problem for accurate and efficient human body detection in the field of computer vision. However, the complex backgrounds, various body postures, occlusions, shadow and so forth that usually have a negative impact on the performance of human body detection. Besides, the real-time ability of the existing detection algorithms are limited in the practical application. In this paper, with the excellent learning ability, a fast and efficient deep convolution neural network based on the YOLOv2 network is presented for real-time human body detection. It is a 22-layer network that is capable to handle the dataflow in 93.5 fps, fully meets the real-time requirements. In the same time, it achieves 80.27% average precision in the complex natural scene.

Keywords

Human body detection YOLOv2 DNN Fast network Real-time ability 

Notes

Acknowledgements

This work was supported by Natural Science Foundation of Beijing Municipality (No. 4182038) and National Science Foundation of China (No. 61671054).

References

  1. 1.
    Liu, S., Su, T., Wang, B., Peng, S., Jin, X., Bai, Y., Dou, C.: Pedestrian indoor navigation using foot-mounted imu with multi-sensor data fusion. Int. J. Model. Ident. Control 30(4), 261–272 (2018)CrossRefGoogle Scholar
  2. 2.
    Liu,Y., Geng, J., Su, Z., Zhang, W., Li, J.: Real-time classification of steel strip surface defects based on deep CNNs. In: Proceedings of 2018 Chinese Intelligent Systems Conference, pp. 257–266. Springer, Berlin (2019)Google Scholar
  3. 3.
    Lienhart, R., Maydt, J.: An extended set of haar-like features for rapid object detection. In: Proceedings. International Conference on Image Processing, vol. 1, p. I. IEEE, New York (2002)Google Scholar
  4. 4.
    Ke, Y., Sukthankar, Rahul, et al.: PCA-SIFT: a more distinctive representation for local image descriptors. CVPR 2(4), 506–513 (2004)Google Scholar
  5. 5.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: International Conference on Computer Vision & Pattern Recognition (CVPR’05), vol. 1, pp. 886–893. IEEE Computer Society (2005)Google Scholar
  6. 6.
    Joachims, T.: Making large-scale SVM learning practical. Technical report, SFB 475: Komplexitätsreduktion in Multivariaten (1998)Google Scholar
  7. 7.
    Gao, K., Su, S., Li, D.-Y., Zhang, S.S., Wang, J.S.: A sentiment analysis approach based on exploiting Chinese linguistic features and classification. Int. J. Model. Ident. Control, 29(3):226–232 (2018)CrossRefGoogle Scholar
  8. 8.
    Viola, P., Jones, Michael, et al.: Rapid object detection using a boosted cascade of simple features. CVPR 1(1), 511–518 (2001)Google Scholar
  9. 9.
    Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition (2008)Google Scholar
  10. 10.
    Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science, 313(5786), 504–507 (2006)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  12. 12.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, pp. 818–833. Springer, Berlin (2014)CrossRefGoogle Scholar
  13. 13.
    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 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  16. 16.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)Google Scholar
  17. 17.
    Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)Google Scholar
  18. 18.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)Google Scholar
  19. 19.
    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: Single shot multibox detector. In: European Conference on Computer Vision, pp. 21–37. Springer, Berlin (2016)CrossRefGoogle Scholar
  20. 20.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)Google Scholar
  21. 21.
    Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)Google Scholar
  22. 22.
    Jasim, W., Gu, D.: Robust path tracking control for quadrotors with experimental validation. Int. J. Model. Ident. Control 29(1), 1–13 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Xiaopeng Liu
    • 1
    • 2
  • Yan Liu
    • 1
    • 2
  • Hong Wang
    • 1
    • 2
  • Jiangyun Li
    • 1
    • 2
    Email author
  1. 1.School of Automation & Electrical EngineeringUniversity of Science and Technology BeijingBeijingChina
  2. 2.Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of EducationBeijingChina

Personalised recommendations