Skip to main content

Advertisement

Springer Nature Link
Log in

Combination of high-level features with low-level features for detection of pedestrian

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

In this paper, we present two high-level features for combining with low-level features. The reason for our use of “high level” and “low level” terms is the ability of features in extracting global and local, respectively, specifications of the objects. We specify the detection result of each feature for a given sample by a score and then add the score of all features to make the final decision. Evaluation results over the cropped images of INRIA dataset for three low-level features including histogram of gradient (HOG), convolutional neural network and Haar, in combination with neural network and SVM as the classifier, show that combining the high-level features with different low-level features, on average, leads to 2.5–7 % increase in detection rate (DR). Also evaluation results on full images of INRIA dataset for two different detectors including: HOG \(+\) neural network and channel features \(+\) boosted decision tree reveal an increase of approximately 5 and 3 % in DR for these two detectors, respectively. Repeating the experiments on more challenging datasets such as Caltech and TUD-Brussels also show an increase of approximately 3 and 1 % for these two detectors, respectively. Overall, combining the high-level features with the low-level features yields at least an increase of 1 % in DR and in some cases, the increase value even reaches to a maximum of 5 %, while the surplus computational burden is only 8 % more than the original detectors.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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. Walk, S., Majer, N., Schindler, K., Schiele, B.: New features and insights for pedestrian detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010. pp. 1030–1037 (2010)

  2. Geronimo, D., Lopez, A.M., Sappa, A.D., Graf, T.: Survey of pedestrian detection for advanced driver assistance systems. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1239–1258 (2010)

    Article  Google Scholar 

  3. Papageorgiou, C., Poggio, T.: A trainable system for object detection. Int. J. Comput. Vis. 38, 15–33 (2000)

    Article  MATH  Google Scholar 

  4. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005. vol. 1, pp. 886–893 (2005)

  5. Namjoo, E., Aghagolzadeh, A., Moin, M.S., Akbari, A.: A novel approach for skin region extraction in color images. In: Proceeding of the 2007 IEEE International Conference on Signal Processing and Communication. Dubai, UAE (2007)

  6. Paisitkriangkrai, S., Shen, C., Zhang, J.: Real-time pedestrian detection using a boosted multi-layer classifier. In: The Eighth International Workshop on Visual Surveillance (Sep 2008)

  7. Phung, S.L., Bouzerdoum, A.: A new image feature for fast detection of people in images. Int. J. Inf. Syst. Sci. 3, 383–391 (2007)

    Google Scholar 

  8. Ma, G., Muller, D., Park, S.B., Schneiders, S.M., Kummert, A.: Pedestrian detection using a single monochrome camera. IET Intel. Transp. Syst. 3, 42–56 (2008)

    Article  Google Scholar 

  9. Cheng, H., Zheng, N., Qin, J.: Pedestrian detection using sparse gabor filter and support vector machine. In: IEEE Intelligent Vehicles Symposium. pp. 583–587 (Sep 2005)

  10. Wu, H., Liu, N., Luo, X., Su, J., Chen, L.: Real-time background subtraction-based video surveillance of people by integrating local texture patterns. In: Signal, Image and Video Processing, vol. 8, pp. 665–676 (2014). 01 May 2014

  11. Barhoumi, W.: Detection of highly articulated moving objects by using co-segmentation with application to athletic video sequences. In: Signal, Image and Video Processing. pp. 1–11 (2014). 15 March 2014

  12. Vázquez, C., Ghazal, M., Amer, A.: Feature-based detection and correction of occlusions and split of video objects. In: Signal, Image and Video Processing, vol. 3, pp. 13–25 (2009). 01 Feb 2009

  13. Portelo, A., Figueiredo, M.T., Lemos, J., Marques, J.: Moving horizon estimation of pedestrian interactions using multiple velocity fields. In: Signal, Image and Video Processing, pp. 1–9 (2014). 21 March 2014

  14. Geronimo, D., Sappa, A., Lopez, A., Ponsa, D.: Adaptive image sampling and windows classification for on-board pedestrian detection. In: Proceeding 5th International Conference on Computer Vision Systems. Bielefeld, Germany (Mar 2007)

  15. Bo, W., Nevatia, R.: 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, 90–97 (2005)

  16. Bo, W., Nevatia, R.: Simultaneous Object, Segmentation by Boosting Local Shape Feature based Classifier. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR’07. pp. 1–8 (2007)

  17. Sabzmeydani, P., Mori, G., Pedestrians, Detecting, by Learning Shapelet Features. In: IEEE conference on computer vision and pattern recognition, CVPR’07. pp. 1–8 (2007)

  18. Shashua, A., Gdalyahu, Y., Hayun, G.: Pedestrian detection for driving assistance systems: single-frame classification and system level performance. In: Intelligent Vehicles Symposium. pp. 1–6 (2004)

  19. Sotelo, M.A., Parra, I., Fernandez, D., Naranjo, E.: Using, pedestrian detection, SVM and multi-feature combination. In: IEEE Intelligent Transportation Systems Conference, ITSC’06. pp. 103–108 (2006)

  20. Suard, F., Rakotomamonjy, A., Bensrhair, A.: Model selection in pedestrian detection using multiple kernel learning. In: IEEE Intelligent Vehicles Symposium 2007, pp. 270–275 (2007)

  21. Grubb, G., Zelinsky, A., Nilsson, L., Rilbe, M.: 3D vision sensing for improved pedestrian safety. In: IEEE Intelligent Vehicles Symposium 2004, pp. 19–24 (2004)

  22. Freund, Y., Schapire, R.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55, 119–139 (1997)

    Article  MATH  MathSciNet  Google Scholar 

  23. Schapire, R., Singer, Y.: Improved boosting algorithms using confidence-rated predictions. Mach. Learn. 37, 297–336 (1999)

    Article  MATH  Google Scholar 

  24. Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)

    Google Scholar 

  25. Oliveira, L., Nunes, U., Peixoto, P.: On exploration of classifier ensemble synergism in pedestrian detection. IEEE Trans. Intell. Transp. Syst. 11, 16–27 (2010)

    Article  Google Scholar 

  26. Allili, M., Ziou, D.: Active contours for video object tracking using region, boundary and shape information. Signal, Image and Video Processing 1, 101–117 (2007)

    Article  MATH  Google Scholar 

  27. Zaki, M., Youssef, M.: TNRAC: a system for tracking multiple moving non-rigid objects using an active camera. Signal, Image and Video Processing 3, 145–155 (2009)

    Article  Google Scholar 

  28. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)

    Article  Google Scholar 

  29. Takarli, F., Aghagolzadeh, A., Seyedarabi, H.: Robust pedestrian detection using low level and high level features. In: 21st Iranian Conference on Electrical Engineering (ICEE), 2013, pp. 1–6 (2013)

  30. Liu, Y., Zeng, L., Huang, Y.: An efficient HOG-ALBP feature for pedestrian detection. In: Signal, Image and Video Processing, pp. 1–10 (2014). 2014/06/20

  31. Xu, Y.W., Cao, X.B., Qiao, H.: Detection, pedestrian, with local feature assistant. In: IEEE International Conference on Control and Automation, ICCA 2007. pp. 1542–1547 (2007)

  32. Kukharev, G., Nowosielski, A.: Visitor identification—elaborating real time face recognition system. WSCG (Short Papers), pp. 157–164 (2004)

  33. Dollar, P., Belongie, S., Perona, P.: The Fastest Pedestrian Detector in the West. Presented at the British Machine Vision Conference (BMVC) (2010)

Download references

Author information

Authors and Affiliations

  1. Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran

    Fariba Takarli & Hadi Seyedarabi

  2. Faculty of Electrical and Computer Engineering, Babol University of Technology, Babol, Iran

    Ali Aghagolzadeh

Authors
  1. Fariba Takarli
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Ali Aghagolzadeh
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Hadi Seyedarabi
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Ali Aghagolzadeh.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Takarli, F., Aghagolzadeh, A. & Seyedarabi, H. Combination of high-level features with low-level features for detection of pedestrian. SIViP 10, 93–101 (2016). https://doi.org/10.1007/s11760-014-0706-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-014-0706-8

Keywords