Advertisement

Real-time pedestrian detection with deep supervision in the wild

  • Zhaoqing Li
  • Zhenxue ChenEmail author
  • Q. M. Jonathan Wu
  • Chengyun Liu
Original Paper
  • 21 Downloads

Abstract

Pedestrian detection is a challenging research task, and it is widely applied in automatic driving and intelligent surveillance fields. Although many approaches based on deep learning have shown effectiveness for detecting pedestrian, these approaches are difficult to achieve a good trade-off between real time and accuracy. In this paper, a new pedestrian detection algorithm is proposed to address the above problem, and then, a new pedestrian dataset is introduced to evaluate detection performance in our experiment. Our model contains region generation module and region prediction module, and our model allows for parallel processing of two modules for speed. The feature pyramid strategy is adopted in generation module to make full use of features, and deconvolution layers are used to obtain more high-level feature contextual. The deep supervision idea is introduced to prediction module to guide the detection results toward ground truth. Eventually, the proposed method is evaluated on three different datasets (INRIA, ETH and Caltech) and compared with other existing state-of-the-arts, and the experimental results present the competitive accuracy and real time of the proposed method.

Keywords

Pedestrian detection Deep supervision Real time Feature pyramid 

Notes

Funding

The funding was provided by National Natural Science Foundation of China (Grand Nos. 61203261; 61876099) and China Postdoctoral Science Foundation-funded project (Grand No. 2012M521335).

References

  1. 1.
    Benenson, R., Omran, M., Hosang, J., Schiele, B.: Ten years of pedestrian detection, what have we learned? Eur. Conf. Comput. Vis. 8926, 613–627 (2014)Google Scholar
  2. 2.
    Cai, Z., Saberian, M., Vasconcelos, N.: Learning complexity aware cascades for deep pedestrian detection. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 3361–3369 (2015)Google Scholar
  3. 3.
    Du, X., El-Khamy, M., Lee, J., Davis, L.: Fused dnn: a deep neural network fusion approach to fast and robust pedestrian detection. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 953–961 (2017)Google Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 1, pp. 886–893 (2005)Google Scholar
  5. 5.
    Perona, P., Dollar, P., Schiele B., Wojek, C.: http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians
  6. 6.
    Dollar, P., Tu, Z., Tao, H., Belongie, S.: Feature mining for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, 2007, CVPR’07, pp. 1–8 (2007)Google Scholar
  7. 7.
    Dollr, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1532–1545 (2014)CrossRefGoogle Scholar
  8. 8.
    Dollr, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743–761 (2011)CrossRefGoogle Scholar
  9. 9.
    Ess, A., Leibe, B., Gool, L.V.: Depth and appearance for mobile scene analysis. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  10. 10.
    Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, vol. 8, pp. 1–8 (2008)Google Scholar
  11. 11.
    Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: Dssd: deconvolutional single shot detector. In: Computer Vision and Pattern Recognition (2017)Google Scholar
  12. 12.
    Ghorban, F., Marn, J., Su, Y., Colombo, A., Kummert, A.: Aggregated channels network for real-time pedestrian detection. In: Computer Vision and Pattern Recognition (2018)Google Scholar
  13. 13.
    Girshick, R.: Fast r-cnn. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448 (2015)Google Scholar
  14. 14.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580–587 (2014)Google Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)Google Scholar
  16. 16.
    Lan, X., Ye, M., Zhang, S., Yuen, P.C.: Robust collaborative discriminative learning for rgb-infrared tracking. In: AAAI Conference on Artificial Intelligence, pp. 7008–7015 (2018)Google Scholar
  17. 17.
    Lee, C., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. AISTATS 38, 09 (2014)Google Scholar
  18. 18.
    Lee, A.Y., Kim, H., Park, E., Cui, X., Kim, H.: Wide-residual-inception networks for real-time object detection. In: 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 758–764 (2017)Google Scholar
  19. 19.
    Lin, Z., Davis, L.S.: A pose-invariant descriptor for human detection and segmentation. Eur. Conf. Comput. Vis. 5305, 423–436 (2008)Google Scholar
  20. 20.
    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: Ssd: single shot multibox detector. Eur. Conf. Comput. Vis. 9905, 21–37 (2016)CrossRefGoogle Scholar
  21. 21.
    Maji, S., Berg, A.C., Malik, J:. Classification using intersection kernel support vector machines is efficient. In: IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008, pp. 1–8 (2008)Google Scholar
  22. 22.
    Nam, W., Dollr, P., Han, J.H.: Local decorrelation for improved pedestrian detection. In: NIPS, vol. 1, pp. 1–9 (2014)Google Scholar
  23. 23.
    Ouyang, W., Wang, X.: Joint deep learning for pedestrian detection. In: 2013 IEEE International Conference on Computer Vision, pp. 2056–2063 (2013)Google Scholar
  24. 24.
    Paisitkriangkrai, S., Shen, C., Hengel, A., Van, D.: Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features. Springer, Berlin (2014)CrossRefGoogle Scholar
  25. 25.
    Pedro, P.O., Lin, T.Y., Collobert, R., Dollr, P.: Learning to refine object segments. In: Lecture Notes in Computer Science, vol. 9905, pp. 75–91 (2016)Google Scholar
  26. 26.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788 (2016)Google Scholar
  27. 27.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149 (2017)CrossRefGoogle Scholar
  28. 28.
    Shen, W., Zhao, K., Jiang, Y., Wang, Y., Bai, X., Yuille, A.: Deepskeleton: learning multi-task scale-associated deep side outputs for object skeleton extraction in natural images. IEEE Trans. Image Process. 26(11), 5298–5311 (2017)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Tom, D., Monti, F., Baroffio, L., Bondi, L., Tagliasacchi, M., Tubaro, S.: Deep convolutional neural networks for pedestrian detection. Signal Process. Image Commun. 47(C), 482–489 (2016)CrossRefGoogle Scholar
  30. 30.
    Viola, P., Jones, M.J., Snow, D.: Detecting pedestrians using patterns of motion appearance. Int. J. Comput. Vis. 2(2), 734–741 (2003)Google Scholar
  31. 31.
    Wojek, C., Schiele, B.: A performance evaluation of single and multi-feature people detection. DAGM Symp. Pattern Recognit. 4(4), 82–91 (2008)CrossRefGoogle Scholar
  32. 32.
    Xie, S., Tu, Z.: Holistically-nested edge detection. Int. J. Comput. Vis. 125(1), 3–18 (2017)MathSciNetCrossRefGoogle Scholar
  33. 33.
    Yang, B., Yan, J., Lei, Z., Li, S. Z.: Convolutional channel features. In: 2015 IEEE International Conference on Computer Vision, pp. 82–90 (2015)Google Scholar
  34. 34.
    Zhang, L., Lin, L., Liang, X., He, K.: Is faster r-cnn doing well for pedestrian detection? Eur. Conf. Comput. Vis. 9906, 443–457 (2016)Google Scholar
  35. 35.
    Zhang, S., Benenson, R., Omran, M., Hosang, J., Schiele, B.: Towards reaching human performance in pedestrian detection. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2018)Google Scholar
  36. 36.
    Zhang, X., Cheng, L., Li, B., Hu, H.M.: Too far to see? Not really!—pedestrian detection with scale-aware localization policy. IEEE Trans. Image Process. 27(8), 3703–3715 (2018)MathSciNetCrossRefGoogle Scholar
  37. 37.
    Zhang, Z., Qiao, S., Xie, C., Shen, W., Wang, B., Yuille, A.: Single-shot object detection with enriched semantics. In: Computer Vision and Pattern Recognition, vol. 12 (2017)Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Control Science and EngineeringShandong UniversityJinanChina
  2. 2.Department of Electrical and Computer EngineeringUniversity of WindsorWindsorCanada

Personalised recommendations