Skip to main content
SpringerLink
Log in

Real-time multi-class object detection using two-dimensional index

  • Original Research Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

When there exists only one sample for each category of objects, previous approaches of training multi-class classifiers are not applicable. In this paper, we propose a new template matching method that is both robust and real-time to multi-class object detections. Firstly, object features are encoded as binary codes based on both quantized gradient intensity and quantized gradient orientation mappings. Then, a two-dimensional index table is constructed. This two-dimensional index table has advantages in effectively organizing relationships between the features from the multi-class templates and their corresponding locations in the templates. For a target image, the features are firstly encoded. Then the object is localized by voting based on the queries of features from the index table. Our experiments on two public data sets demonstrate the high efficiency of our method and the superior performance to the state-of-the-art methods.

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

Similar content being viewed by others

References

  1. Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. TPAMI 26(11), 1475–1490 (2004)

    Article  Google Scholar 

  2. Babenko, B., Yang, M.H., Belongie, S.: Visual tracking with online multiple instance learning. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Miami, FL (2009)

  3. Benenson, R., Mathias, M., Timofte, R. et al.: Pedestrian detection at 100 frames per second. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Providence, RI (2012)

  4. Brunelli, R.: Template Matching Techniques in Computer Vision: Theory and Practice. Wiley, New York (2009)

    Book  Google Scholar 

  5. Quinn, P.C., Eimas, P.D., Tarr, M.J.: Perceptual categorization of cat and dog silhouettes by 3-to-4 month old infants. J. Exp. Child Psychol. 79(1), 78–94 (2001)

    Article  Google Scholar 

  6. Comaniciu, D., Meer, P.: Mean shift analysis and applications. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision (1999)

  7. Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. TPAMI 32(9), 1627–1645 (2009)

    Article  Google Scholar 

  8. Fidler, S., Boben, M., Leonardis, A.: A coarse-to-fine taxonomy of constellations for fast multi-class object detection. In: ECCV (2010)

  9. Fidler, S., Leonardis, A.: Towards scalable representation of object categories: learning a hierarchy of parts. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Minneapolis, MN (2007)

  10. Gall, J., Lempitsky, V.: On feature combination for multiclass object detection. In: IEEE 12th International Conference on Computer Vision, Kyoto (2009)

  11. Hinterstoisser, S., Cagniart, C., Ilic, S.: Gradient response maps for real-time detection of textureless objects. TPAMI 34, 876–888 (2012)

    Article  Google Scholar 

  12. Chen, J.H., Chen, C.S., Chen, Y.S.: Fast algorithm for robust template matching with M-estimators. IEEE Trans. Signal Process. 51(1), 230–243 (2003)

    Article  MathSciNet  MATH  Google Scholar 

  13. Seo, H.J., Milanfar, P.: Training-free, generic object detection using locally adaptive regression kernels. TPAMI 32(9), 1688–1704 (2010)

    Article  Google Scholar 

  14. Kappor, A., Winn, J.: Located Hidden Random Fields: Learning Discriminative Parts for Object Detection. In: ECCV, vol. 3954, pp. 302–315 (2006)

  15. Lampert, C.H., Blaschko, M.B., Hofmann, T.: Efficient subwindow search: a branch and bound framework for object localization. TPAMI 31(12), 2129–2142 (2009)

    Article  Google Scholar 

  16. Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. In: IJCV, pp. 1–23 (2010)

  17. Ling, H., Soatto, S., Ramanathan, N., Jacobs, D.W.: Face verification across age progression using discriminative methods. TIFS 5(1), 82–91 (2010)

    Google Scholar 

  18. Lowe, D.: Distinctive image features from scale-invariant keypoints. In: IJCV (2004)

  19. Masnadi-Shirazi, H., Vasconcelos, N.: High detection-rate cascades for real-time object detection. In: ICCV, pp. 1–6 (2007)

  20. Mutch, J., Lowe, D.G.: Multiclass object recognition with sparse, localized features. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 11–18. New York, USA (2006)

  21. Opelt, A., Pinz, A., Zisserman, A.: Learning an alphabet of shape and appearance for multi-class object detection. In: IJCV, pp. 16–44 (2008)

  22. Razavi, N., Gall, J., Gool, L.V.: Scalable multi-class object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Providence, RI (2011)

  23. Santner, J., Leistner, C., Saffari, A., Pock, T., Bischof, H.: PROST: parallel robust online simple tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, San Francisco, CA (2010)

  24. Shechtman, E., Irani, M.: Matching local self-similarities across images and videos. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 1–8. Minneapolis, MN (2007)

  25. Shechtman, E., Irani, M.: Space–time behavior-based correlation-or-how to tell if two underlying motion fields are similar without computing them. TPAMI 29(11), 2045–2056 (2007)

    Article  Google Scholar 

  26. Sibiryakov, A.: Fast and high-performance template matching method. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Providence, RI (2011)

  27. Steger, C.: Occlusion clutter, and illumination invariant object recognition. In: IAPRS (2002)

  28. Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing visual features for multiclass and multiview object detection. TPAMI 29(5), 854–869 (2007)

    Article  Google Scholar 

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

    Article  MATH  Google Scholar 

  30. Chen, J., Shan, S., He, C., Zhao, G., Pietikainen, M., Chen, X., Gao, W.: A robust local image descriptor. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1705–1720 (2010)

    Article  Google Scholar 

  31. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. IEEE Int’l Conf, Computer Vision and Pattern Recognition (2005)

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

    Article  Google Scholar 

  33. Zitnick, L.: Binary coherent edge descriptors. Eur. Conf. Comput. Vis. 6312, 170–182 (2010)

    Google Scholar 

Download references

Acknowledgments

This work was supported in part by the National Natural Science Foundation of China (61375038).

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, Center for Robotics, University of Electronic Science and Technology of China, Chengdu, 611731, People’s Republic of China

    Yumin Dou, Pei Xu, Mao Ye, Xue Li, Lishen Pei & Xudong Li

Authors
  1. Yumin Dou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pei Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mao Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xue Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Lishen Pei
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xudong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mao Ye.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dou, Y., Xu, P., Ye, M. et al. Real-time multi-class object detection using two-dimensional index. J Real-Time Image Proc 16, 243–253 (2019). https://doi.org/10.1007/s11554-015-0525-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-015-0525-3

Keywords

Search

Navigation