Advertisement

Multimedia Tools and Applications

, Volume 76, Issue 23, pp 25079–25089 | Cite as

Pedestrian detection based on multi-convolutional features by feature maps pruning

  • Ting Rui
  • Junhua Zou
  • You Zhou
  • Husheng Fang
  • Qiyu Gao
Article

Abstract

Convolutional neural network (CNN) has developed such a large network size in last few years, so reducing the storage requirement without hurting its accuracy becomes necessary. In this paper, in order to reduce the number of high dimensional feature maps in shallow layers, we propose a feature map selection method, which cuts the feature map number by correlation coefficient between kernels and finishes detection by HOG+SVM method. Firstly, we extract feature maps of shallow layers from trained CNN. Then, we merge strongly relevant feature maps and choose all maps among weakly relevant feature maps by analyzing correlation coefficient of kernels. Finally, we extract HOG features of the chosen feature maps and use SVM to complete the training and classification. The experimental results show that the proposed method can effectively prune high dimensional feature maps and stabilize or even advance the performance in pedestrian detection.

Keywords

Pedestrian detection Convolutional neural network Feature maps pruning Histogram of oriented gradient 

Notes

Acknowledgments

This work was supported in part by National Natural Science Foundation of China: 61472444, 61472392.

References

  1. 1.
    Abdel-Hamid O, Mohamed AR, Jiang H, Penn G (2012) Applying convolutional neural networks concepts to hybrid nn-hmm model for speech recognition. In: 2012 IEEE international conference on Acoustics, speech and signal processing (ICASSP), pp 4277–4280. IEEEGoogle Scholar
  2. 2.
    Barinova O, Lempitsky V, Kholi P (2012) On detection of multiple object instances using hough transforms. IEEE Trans Pattern Anal Mach Intell 34(9):1773–1784CrossRefGoogle Scholar
  3. 3.
    Bertozzi M, Broggi A, Del Rose M, Felisa M, Rakotomamonjy A, Suard F (2007) A pedestrian detector using histograms of oriented gradients and a support vector machine classifier. In: 2007 IEEE Intelligent Transportation Systems Conference, pp 143–148. IEEEGoogle Scholar
  4. 4.
    Chen W, Wilson JT, Tyree S, Weinberger KQ, Chen Y (2015) Compressing neural networks with the hashing trick. Computer Science, pp 2285–2294Google Scholar
  5. 5.
    Dalal N, Triggs B (2005) 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. IEEEGoogle Scholar
  6. 6.
    Dollar P, Wojek C, Schiele B, Perona P (2012) Pedestrian detection: An evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34(4):743–761CrossRefGoogle Scholar
  7. 7.
    Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35(8):1915–1929CrossRefGoogle Scholar
  8. 8.
    Gong Y, Liu L, Yang M, Bourdev L (2014) Compressing deep convolutional networks using vector quantization. Computer ScienceGoogle Scholar
  9. 9.
    Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Ji S, Xu W, Yang M, Yu K (2013) 3d convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35(1):221–231CrossRefGoogle Scholar
  12. 12.
    Jia HX, Zhang YJ (2007) Fast human detection by boosting histograms of oriented gradients. In: 2007. ICIG 2007. Fourth International Conference on Image and Graphics, pp 683–688. IEEEGoogle Scholar
  13. 13.
    John V, Mita S, Liu Z, Qi B (2015) Pedestrian detection in thermal images using adaptive fuzzy c-means clustering and convolutional neural networks. In: 2015 14th IAPR International Conference on Machine Vision Applications (MVA), pp 246–249. IEEEGoogle Scholar
  14. 14.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105Google Scholar
  15. 15.
    Le QV (2013) Building high-level features using large scale unsupervised learning. In: 2013 IEEE international conference on acoustics, speech and signal processing, pp 8595–8598. IEEEGoogle Scholar
  16. 16.
    Ouyang W, Luo P, Zeng X, Qiu S, Tian Y, Li H, Yang S, Wang Z, Xiong Y, Qian C et al (2014) Deepid-net: multi-stage and deformable deep convolutional neural networks for object detection. arXiv:1409.3505
  17. 17.
    Ouyang W, Wang X (2013) Joint deep learning for pedestrian detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2056–2063Google Scholar
  18. 18.
    Ouyang W, Zeng X, Wang X (2016) Learning mutual visibility relationship for pedestrian detection with a deep model. International Journal of Computer Vision, pp 1–14Google Scholar
  19. 19.
    Tuzel O, Porikli F, Meer P (2008) Pedestrian detection via classification on riemannian manifolds. IEEE Trans Pattern Anal Mach Intell 30(10):1713–1727CrossRefGoogle Scholar
  20. 20.
    Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol 1, pp I–511. IEEEGoogle Scholar
  21. 21.
    Wang T, Wu DJ, Coates A, Ng AY (2012) End-to-end text recognition with convolutional neural networks. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp 3304–3308. IEEEGoogle Scholar
  22. 22.
    Zhu Q, Yeh MC, Cheng KT, Avidan S (2006) Fast human detection using a cascade of histograms of oriented gradients. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), vol 2, pp 1491–1498. IEEEGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.PLA University of Science and TechnologyQinhuai District NanjingChina
  2. 2.State Key Laboratory for Novel Software TechnologyNanjing UniversityNanjing ShiChina
  3. 3.College of Machanical EngineeringJiangsu Institute of CommerceQinhuai District NanjingChina

Personalised recommendations