Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Sparse representation-based human detection: a scale-embedded dictionary approach

  • 421 Accesses

  • 5 Citations


Human detection is a complex problem owing to the variable pose that they can adopt. Here, we address this problem in sparse representation framework with an overcomplete scale-embedded dictionary. Histogram of oriented gradient features extracted from the candidate image patches are sparsely represented by the dictionary that contain positive bases along with negative and trivial bases. The object is detected based on the proposed likelihood measure obtained from the distribution of these sparse coefficients. The likelihood is obtained as the ratio of contribution of positive bases to negative and trivial bases. The positive bases of the dictionary represent the object (human) at various scales. This enables us to detect the object at any scale in one shot and avoids multiple scanning at different scales. This significantly reduces the computational complexity of detection task. In addition to human detection, it also finds the scale at which the human is detected due to the scale-embedded structure of the dictionary.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12


  1. 1.

    Krishna Vinay, G., Haque, Sk. M., Venkatesh Babu, R., Ramakrishnan, K.R.: Human detection using sparse representation. In: ICASSP (2012)

  2. 2.

    Chen, S.S., Donoho, D.L., Saunders, M.A.: Atomic decomposition by basis pursuit. SIAM J. Sci. Comput. 20(1), 33–61 (1998)

  3. 3.

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

  4. 4.

    Viola, P., Jones, M.: Robust real-time object detection. Int. J. Comput. Vis. 57(2), 137–154 (2001)

  5. 5.

    Mohan, A., Papageorgiou, C., Poggio, T.: Example based object detection in images by components. IEEE Trans. Pattern Anal. Mach. Intel. 23, 349–361 (2001)

  6. 6.

    Laptev, I.: Improvements of object detection using boosted histograms. In: BMVC (2006)

  7. 7.

    Felzenszwalb, P., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intel. 32(9), 1627–1645 (2010)

  8. 8.

    Liu, Y., Zeng, L., Huang, Y.: An efficient HOG—ALBP feature for pedestrian detection. Signal Image Video Process. 8(1), 125–134 (2014)

  9. 9.

    Takarli, F., Aghagolzadeh, A., Seyedarabi, H.: Combination of high-level features with low-level features for detection of pedestrian. Signal Image Video Process. 1–9 (2014). doi:10.1007/s11760-014-0706-8

  10. 10.

    Xu, R., Zhang, B., Ye, Q., Jiao, J.: Human detection in images via \(l_1\)-norm minimization learning. In: ICASSP (2010)

  11. 11.

    Xu, R., Zhang, B., Ye, Q., Jiao, J.: Cascaded \(l_1\)-norm minimization learning (CLML) for human detection. In: CVPR (2010)

  12. 12.

    Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intel. 31(2), 210–227 (2009)

  13. 13.

    Wang, X., Wang, Y., Wan, W., Hwang, J.-N.: Object tracking with sparse representation and annealed particle filter. Signal Image Video Process. 8(6), 1059–1068 (2014)

  14. 14.

    Sivalingam, R., Somasundaram, G., Morellas, V., Papanikolopoulos, N., Lotfallah, O., Park, Y.: Dictionary learning based object detection and counting in traffic scenes. In: ICDSC (2010)

  15. 15.

    Mei, X., Ling, H.: Robust visual tracking and vehicle classification via sparse representation. IEEE Trans. Pattern Anal. Mach. Intel. 33(11), 2259–2272 (2011)

  16. 16.

    Naresh Kumar, M.S., Parate Priti, Venkatesh Babu, R.: Fragment-based real-time object tracking: A sparse representation approach. In: ICIP (2012)

  17. 17.

    Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)

  18. 18.

    Sinha, N., Venkatesh Babu, R.: Optic disk localization using \(l_1\) minimization. In: ICIP (2012)

  19. 19.

    Guo, K., Ishwar, P., Konrad, J.: Action recognition using sparse representation on covariance manifolds of optical flow. In: ICIP (2010)

  20. 20.

    Amaldi, E., Kann, V.: On the approximability of minimizing nonzero variables or unsatisfied relations in linear systems. Theor. Comput. Sci. 209, 237–260 (1998)

  21. 21.

    Donoho, D.L.: For most large underdetermined systems of linear equations the minimal \(l\)1-norm solution is also the sparsest solution. Comm. Pure Appl. Math 59, 797–829 (2004)

  22. 22.

    Candes, E., Wakin, M., Boyd, S.: Enhancing sparsity by reweighted \(l_1\) minimization. J. Fourier Anal. Appl. 14, 877–905 (2008)

  23. 23.

    Dalal, N., Triggs, B.: Histogram of oriented gradients for human detection. In: CVPR (2005)

  24. 24.

    Overett, G., Petersson, L., Brewer, N., Andersson, L., Pettersson, N.: A new pedestrian dataset for supervised learning. In: IEEE Intelligent Vehicles Symposium, pp. 373–378 (2008)

  25. 25.

    Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online learning for matrix factorization and sparse coding. J. Mach. Learn. Res. 11, 19–60 (2010)

Download references

Author information

Correspondence to R. Venkatesh Babu.

Additional information

An earlier brief version of this paper has appeared in ICASSP-2012 [1].

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Krishna Vinay, G., Haque, S.M., Venkatesh Babu, R. et al. Sparse representation-based human detection: a scale-embedded dictionary approach. SIViP 10, 585–592 (2016). https://doi.org/10.1007/s11760-015-0781-5

Download citation


  • Human detection
  • Histogram of oriented gradients (HOG)
  • \(l_{1}\)-Norm minimization
  • Sparse representation
  • Sparse classification
  • Scale-embedded dictionary