Skip to main content
SpringerLink
Log in

Pedestrian detection based on the privileged information

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The pedestrian detection is always a challenging issue in the computer vision. Unlike the object recognition problem, the detection’s speed is a critical factor. In order to accelerate detection speed while maintaining competitive accuracy, in this paper we introduce a new model: twin support vector machine based on privileged information (called TSVMPI, in this paper) (Qi et al. in Neurocomputing 129:146–152, 1) to detect pedestrian. TSVMPI uses two nonparallel hyperplane classifiers to decide the label of an unknown sample and is superior to the standard SVM, especially in the linear kernel case, resulting in a significant advantage to deal with the special task. All experimental results demonstrate our strategy’s effectiveness and show that the privileged information indeed offers a significant improvement for the pedestrian detection.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. http://www.princeton.edu/~rvdb/loqo/LOQO.html.

  2. \(error\,rate=\frac{\sharp\,Error\,classified}{\sharp\,Total\,samples}\).

  3. When no samples with privileged information are added to TSVMPI, TSVMPI will degenerate to TWSVM [17].

  4. These methods’ code and detection results can be found by the webpage: http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/.

  5. http://www.vision.ee.ethz.ch/~aess/dataset/.

  6. http://www.d2.mpi-inf.mpg.de/tud-brussels.

References

  1. Qi Z, Tian Y, Shi Y (2014) A new classification model using privileged information and its application. Neurocomputing 129:146–152

    Article  Google Scholar 

  2. Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: CVPR, pp. 511–518

  3. Laptev I (2006) Improvements of object detection using boosted histograms. In: BMVC, pp. 949–958

  4. Pang J, Huang Q, Jiang S (2008) Multiple instance boost using graph embedding based decision stump for pedestrian detection. In: ECCV, pp. 541–552

  5. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893

  6. Wang X, Han TX, Yan S (2009) An hog-lbp human detector with partial occlusion handling. In: ICCV, pp. 32–39

  7. Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: CVPR

  8. Maji S, Berg A, Malik J (2008) Classification using intersection kernel support vector machines is efficient. In: CVPR, pp. 1–8

  9. Sudowe P, Leibe B (2011) Efficient use of geometric constraints for sliding-window object detection in video. In: Proceedings of the 8th international conference on Computer vision systems, pp. 11–20

  10. Schwartz WR, Kembhavi A, Harwood D, Davis LS (2009) Human detection using partial least squares analysis. In: CVPR, pp. 24–31

  11. Ding Y, Xiao J (2012) Contextual boost for pedestrian detection. In: CVPR, pp. 2895–2902

  12. Lampert CH, Blaschko MB, Hofmann T (2008) Beyond sliding windows: object localization by efficient subwindow search. In: CVPR

  13. Vapnik V (2006) Estimation of dependences based on empirical data (information science and statistics). Springer, New York

    MATH  Google Scholar 

  14. Vapnik V, Vashist A (2009) A new learning paradigm: learning using privileged information. Neural Netw 22(5–6):544–557

    Article  MATH  Google Scholar 

  15. Pechyony D, Vapnik V (2010) On the theory of learning with privileged information. In: Advances in neural information processing systems 23

  16. Yang H, Patras I. Privileged information-based conditional regression forest for facial feature detection

  17. Jayadeva S, Khemchandani R, Chandra S (2007) Twin support vector machines for pattern classification. IEEE Trans Pattern Anal Mach Intell 29:905–910

    Article  MATH  Google Scholar 

  18. Dollár P, Wojek C, Schiele B, Perona P (2012) Pedestrian detection: an evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34:743–761

    Article  Google Scholar 

  19. Wang P, Shen C, Barnes N, Zheng H (2012) Fast and robust object detection using asymmetric totally corrective boosting. IEEE Trans Neural Netw Learn Syst 23:33–46

    Article  Google Scholar 

  20. Yan J, Zhang X, Lei Z, Liao S, Li SZ (2013) Robust multi-resolution pedestrian detection in traffic scenes. In: CVPR, pp. 3033–3040

  21. Benenson R, Mathias M, Timofte R, Gool LJV (2012) Pedestrian detection at 100 frames per second. In: CVPR, pp. 2903–2910

  22. Enzweiler M, Eigenstetter A, Schiele B, Gavrila DM (2010) Multi-cue pedestrian classification with partial occlusion handling. In: CVPR, pp. 990–997

  23. Torralba A, Murphy K, Freeman W. Contextual models for object detection using boosted random fields. In: Advances in neural information processing systems

  24. Sermanet P, Kavukcuoglu K, Chintala S, LeCun Y. Pedestrian detection with unsupervised multi-stage feature learning. arXiv preprint arXiv:1212.0142

  25. Chen R, Chen W, Yang S, Wu D, Wang Y, Tian Y, Shi Y (2011) Rigorous assessment and integration of the sequence and structure based features to predict hot spots. BMC Bioinformatics 12:311–324

    Article  Google Scholar 

  26. Blum A, Mitchell T (1998) Combining labeled and unlabeled data with co-training. Morgan Kaufmann Publishers, Los Altos

    Book  Google Scholar 

  27. Walk S, Majer N, Schindler K, Schiele B (2010) New features and insights for pedestrian detection. In: CVPR, pp. 1030–1037

  28. Dalal N, Triggs B, Schmid C (2006) Human detection using oriented histograms of flow and appearance. In: ECCV, pp. 428–441

  29. Chang C-C, Lin C-J. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2

  30. Pechyony D, Izmailov R, Vashist A, Vapnik V (2010) Smo-style algorithms for learning using privileged information. In: DMIN, pp. 235–241

  31. Sabzmeydani P, Mori G (2007) Detecting pedestrians by learning shapelet features. In: CVPR, pp. 1–8

  32. Lin Z, Davis LS (2008) A pose-invariant descriptor for human detection and segmentation. In: ECCV, pp. 423–436

  33. Dollár P, Tu Z, Tao H, Belongie S (2007) Feature mining for image classification. In: CVPR

  34. Wojek C, Schiele B (2008) A performance evaluation of single and multi-feature people detection. In: Proceedings of the 30th DAGM symposium on pattern recognition, pp. 82–91

  35. Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32:1627–1645

    Article  Google Scholar 

  36. Bar-Hillel A, Levi D, Krupka E, Goldberg C (2010) Part-based feature synthesis for human detection. In: ECCV (4), pp. 127-142

  37. Dollar P, Belongie S, Perona P (2010) The fastest pedestrian detector in the west. In: Proceedings of the British machine vision conference, pp. 68.1–68.11

  38. Dollár P, Tu Z, Perona P, Belongie S (2009) Integral channel features. In: British machine vision conference

  39. Park D, Zitnick CL, Ramanan D, Dollár P. Exploring weak stabilization for motion feature extraction

  40. Dollár P, Appel R, Kienzle W (2012) Crosstalk cascades for frame-rate pedestrian detection. In: ECCV. Springer, pp. 645–659

  41. Ouyang W, Wang X (2012) A discriminative deep model for pedestrian detection with occlusion handling. In: CVPR, pp. 3258–3265

  42. Shen C, Wang P, Paisitkriangkrai S, van den Hengel A (2013) Training effective node classifiers for cascade classification. Int J Comput Vis, 1–22

  43. Benenson R, Mathias M, Tuytelaars T, Van Gool L (2013) Seeking the strongest rigid detector. In: Proceedings of IEEE conference on computer vision and pattern recognition

  44. Chen G, Ding Y, Xiao J, Han TX (2013) Detection evolution with multi-order contextual co-occurrence. In: CVPR, pp. 1798–1805

  45. Yan J, Zhang X, Lei Z, Liao S, Li SZ (2013) Robust multi-resolution pedestrian detection in traffic scenes. In: CVPR, pp. 3033–3040

  46. Nam W, Han B, Han JH (2011) Improving object localization using macrofeature layout selection. In: ICCV, pp. 1801–1808

  47. Paisitkriangkrai S, Shen C, Hengel AVD. Efficient pedestrian detection by directly optimize the partial area under the roc curve. arXiv preprint arXiv:1310.0900

  48. Ouyang W, Zeng X, Wang X. Modeling mutual visibility relationship in pedestrian detection

  49. Ess A, Leibe B, Schindler K, van Gool L (2008) A mobile vision system for robust multi-person tracking. In: CVPR

  50. Wojek C, Walk S, Schiele B (2009) Multi-cue onboard pedestrian detection. In: CVPR, pp. 1–8. http://www.d2.mpi-inf.mpg.de/tud-brussels

Download references

Acknowledgements

This work has been partially supported by grants from National Natural Science Foundation of China (Nos. 61402429, 61472390, 11271361, 11201472, 11331012), key project of National Natural Science Foundation of China (No. 71331005), and Major International (Regional) Joint Research Project (No. 71110107026).

Author information

Authors and Affiliations

  1. Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing, 100190, China

    Fan Meng, Zhiquan Qi, Yingjie Tian & Lingfeng Niu

  2. Research Center on Fictitious Economy & Data Science, Chinese Academy of Sciences, Beijing, 100190, China

    Fan Meng, Zhiquan Qi, Yingjie Tian & Lingfeng Niu

  3. School of Economics and Management, University of Chinese Academy Sciences, Beijing, 100190, China

    Fan Meng

Authors
  1. Fan Meng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhiquan Qi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yingjie Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lingfeng Niu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhiquan Qi.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Meng, F., Qi, Z., Tian, Y. et al. Pedestrian detection based on the privileged information. Neural Comput & Applic 29, 1485–1494 (2018). https://doi.org/10.1007/s00521-016-2639-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-016-2639-3

Keywords

Search

Navigation