Skip to main content

Advertisement

SpringerLink
Log in

G2P: a new descriptor for pedestrian detection

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

Abstract

Pedestrian detection plays an important role in many applications. Since its birth 13 years ago, Histogram Of Gradient (HOG) descriptor has become a popular descriptor for pedestrian detection. Besides its original instantiation, the HOG also reflects a general methodology of constructing descriptors based on histograms of gradients of certain image sub-blocks. Following this general methodology, a number of HOG-style descriptors have been reported in the literature. The generation process of these descriptors is summarized in this work, and a new descriptor is presented for pedestrian detection. Three contributions are made in this work. First, a general model called descriptor generation model (DGM) is proposed, which can be used to systematically construct a wide range of HOG-style descriptors for pedestrian detection. Second, based on the DGM, a pedestrian detection experimental framework (PDEF) is introduced to find the optimal HOG-style descriptor. In the PDEF, the performance of each descriptor can be evaluated. At last, the genetic algorithm is employed to search the optimal (or semi-optimal) HOG-style descriptor in the descriptor space. And a new descriptor named Second-order Gradient for Pedestrian detection (G2P) is presented. Experimental results demonstrate the advantage of the G2P descriptor over the standard HOG descriptor with ETH, CVC-02-system, NITCA and KITTI dataset, which also reflects the effectiveness of the DGM-based PDEF in finding better descriptors for 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
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Bandyopadhyay T, Won KS, Frazzoli E, Hsu D, Lee WS, Rus D (2013) Intention-aware motion planning. In: Algorithmic foundations of robotics X. Springer, Berlin, pp 475–491

  2. Benenson R, Mathias M, Timofte R, Van Gool L (2012) Fast stixel computation for fast pedestrian detection. In: European conference on computer vision. Springer, Berlin, pp 11–20

  3. Benenson R, Mathias M, Timofte R, Van Gool L (2012) Pedestrian detection at 100 frames per second. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2903–2910

  4. Beyer HG (2013) The theory of evolution strategies. Springer, Berlin

    Google Scholar 

  5. Boyle RD, Thomas RC (1988) Computer vision: a first course. Blackwell, Oxford

    Google Scholar 

  6. Canny J (1986) A computational approach to edge detection. IEEE Trans. Pattern Anal Mach Intell 6:679–698

    Article  Google Scholar 

  7. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297

    MATH  Google Scholar 

  8. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE computer society conference on computer vision and pattern recognition, 2005 (CVPR 2005), vol 1. IEEE, pp 886–893

  9. Ess A, Leibe B, Van Gool L (2007) Depth and appearance for mobile scene analysis. In: IEEE 11th international conference on computer vision, 2007 (ICCV 2007). IEEE, pp 1–8

  10. Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: IEEE conference on computer vision and pattern recognition, 2008 (CVPR 2008). IEEE, pp 1–8

  11. Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645

    Article  Google Scholar 

  12. Gerónimo D, Sappa AD, Ponsa D, López AM (2010) 2d–3d-based on-board pedestrian detection system. Comput Vis Image Underst 114(5):583–595

    Article  Google Scholar 

  13. Hashimoto Y, Yanlei G, Hsu LT, Shunsuke K (2015) A probabilistic model for the estimation of pedestrian crossing behavior at signalized intersections. In: 2015 IEEE 18th international conference on intelligent transportation systems (ITSC). IEEE, pp 1520–1526

  14. Keller CG, Gavrila DM (2014) Will the pedestrian cross? A study on pedestrian path prediction. IEEE Trans Intell Transp Syst 15(2):494–506

    Article  Google Scholar 

  15. Lategahn H, Beck J, Kitt B, Stiller C (2013) How to learn an illumination robust image feature for place recognition. In: 2013 IEEE on intelligent vehicles symposium (IV). IEEE, pp 285–291

  16. Lategahn H, Beck J, Stiller C (2014) Dird is an illumination robust descriptor. In: 2014 IEEE on intelligent vehicles symposium proceedings. IEEE, pp 756–761

  17. Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110

    Article  Google Scholar 

  18. Luo NL, Sullivan PJ, Stout KJ (1993) Gaussian filtering of three-dimensional engineering surface topography. In: measurement technology and intelligent instruments. International Society for Optics and Photonics, pp 527–538

  19. Martinez-Carballido J, Morales-Velázquez M (2012) Using adaptive threshold to detect pedestrians crossing on a street for advanced driver assistance systems. In: 2012 22nd international conference on electrical communications and computers (CONIELECOMP). IEEE, pp 179–182

  20. Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987

    Article  Google Scholar 

  21. Ott P, Everingham M (2009) Implicit color segmentation features for pedestrian and object detection. In: 2009 IEEE 12th international conference on computer vision. IEEE, pp 723–730

  22. Overett G, Petersson L, Brewer N, Andersson L, Pettersson N (2008) A new pedestrian dataset for supervised learning. In: 2008 IEEE intelligent vehicles symposium. IEEE, pp 373–378

  23. Papageorgiou CP, Oren M, Poggio T (1998) A general framework for object detection. In: Sixth international conference on computer vision. IEEE, pp 555–562

  24. Prioletti A, Møgelmose A, Grisleri P, Trivedi MM, Broggi A, Moeslund TB (2013) Part-based pedestrian detection and feature-based tracking for driver assistance: real-time, robust algorithms, and evaluation. IEEE Trans Intell Transp Syst 14(3):1346–1359

    Article  Google Scholar 

  25. Sabzmeydani P, Mori G (2007) Detecting pedestrians by learning shapelet features. In: IEEE conference on computer vision and pattern recognition, 2007 (CVPR’07). IEEE, pp 1–8

  26. Sobel I, Feldman G (1968) A \(3 \times 3\) isotropic gradient operator for image processing. A talk at the Stanford artificial project, pp 271–272

  27. Wang G, Liu Q, Wang Z (2015) Segmentation of far-infrared pedestrians for advanced driver-assistance systems. In: 2015 IEEE international conference on imaging systems and techniques (IST). IEEE, pp 1–6

  28. Wang X, Han TX, Yan S (2009) An HOG-LBP human detector with partial occlusion handling. In: 2009 IEEE 12th international conference on computer vision. IEEE, pp 32–39

  29. Whitley D (1994) A genetic algorithm tutorial. Stat Comput 4(2):65–85

    Article  Google Scholar 

  30. Wu B, Nevatia R (2005) Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors. In: Tenth IEEE international conference on computer vision, 2005 (ICCV 2005), vol 1. IEEE, pp 90–97

  31. Yang M, Qian Y, Xue L, Li H, Deng L, Wang C (2017) G2P: a new descriptor for pedestrian detection. In: IEEE conference on international conference on security, pattern analysis, and cybernetics, 2017 (ICSPAC). IEEE

  32. Zhang H, Cao X, Ho JKL, Chow TWS (2017) Object-level video advertising: an optimization framework. IEEE Trans Ind Inf 13(2):520–531

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. SJTU-ParisTech Elite Institute of Technology, Shanghai Jiao Tong University, 200240, Shanghai, China

    Ming Yang, Yeqiang Qian, Linji Xue, Liuyuan Deng & Chunxiang Wang

  2. Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, 200240, China

    Hao Li

Authors
  1. Ming Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yeqiang Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Linji Xue
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Liuyuan Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chunxiang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chunxiang Wang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Funding

This work is supported by the National Natural Science Foundation of China (U1764264), International Chair on automated driving of ground vehicle. Chunxiang Wang is the corresponding author.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, M., Qian, Y., Xue, L. et al. G2P: a new descriptor for pedestrian detection. Neural Comput & Applic 32, 4665–4674 (2020). https://doi.org/10.1007/s00521-018-3815-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-018-3815-4

Keywords

Search

Navigation