Skip to main content
SpringerLink
Log in

Improving object classification robustness in RGB-D using adaptive SVMs

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Nowadays object recognition is a fundamental capability for an autonomous robot in interaction with the physical world. Taking advantage of new sensing technologies providing RGB-D data, the object recognition capabilities increase dramatically. Object recognition has been well studied, however, known object classifiers usually feature poor generality and, therefore, limited adaptivity to different application domains. Although some domain adaptation approaches have been presented for RGB data, little work has been done on understanding the effects of applying object classification algorithms using RGB-D for different domains. Addressing this problem, we propose and comprehensively investigate an approach for object recognition in RGB-D data that uses adaptive Support Vector Machines (aSVM) and, in this way, achieves an impressive robustness in cross-domain adaptivity. For evaluation, two datasets from different application domains were used. Moreover, a study of state-of-the-art RGB-D feature extraction techniques and object classification methods was performed to identify which combinations (object representation - classification algorithm) remain less affected in terms of performance while switching between different application domains.

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
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Notes

  1. We controlled the expected proportion of false discoveries using the BH step-up procedure for False Discovery Rate control [3], as the tests are independent (between objects) or positively correlated (between 40, 50 and 60 % adaptations).

References

  1. Aldoma A, Marton ZC, Tombari F, Wohlkinger W, Potthast C, Zeisl B, Rusu RB, Gedikli S, Vincze M (2012) Point cloud library: Three-dimensional object recognition and 6 dof pose estimation. IEEE Robot Autom Mag 19(3):80–91

    Article  Google Scholar 

  2. Alexandre LA (2012) 3d descriptors for object and category recognition: a comparative evaluation. In: Workshop on Color-Depth Camera Fusion in Robotics at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vilamoura, Portugal

  3. Benjamini Y, Hochberg Y (1995) Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing. J R Stat Soc Ser B (Methodological) 57(1):289–300. doi:10.2307/2346101

    MathSciNet  MATH  Google Scholar 

  4. Blitzer J, Dredze M, Pereira F (2007) Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. In: ACL, vol 7, pp 440–447

  5. Chang CC, Lin CJ LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2:27:1–27:27. Software available at, http://www.csie.ntu.edu.tw/cjlin/libsvm

  6. Daumé III H (2007) Frustratingly easy domain adaptation. In: ACL, vol 1785, pp 1787

  7. Daumé III H, Marcu D (2006) Domain adaptation for statistical classifiers. J Artif Intell Res (JAIR) 26:101–126

    MathSciNet  MATH  Google Scholar 

  8. Fischler MA, Bolles RC (1981) Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395. doi:10.1145/358669.358692

    Article  MathSciNet  Google Scholar 

  9. Grzegorzek M (2010) A System for 3D Texture-Based Probabilistic Object Recognition and Its Applications. International Journal on Pattern Analysis and Applications 13(3):333–348

    Article  MathSciNet  Google Scholar 

  10. Grzegorzek M, Deinzer F, Reinhold M, Denzler J, Niemann H (2003) How Fusion of Multiple Views Can Improve Object Recognition in Real-World Environments. In: Ertl T, Girod B, Greiner G, Niemann H, Seidel HP, Steinbach E, Westermann R (eds) Vision, Modeling, and Visualization 2003, pp 553–560. Aka/IOS Press, Berlin, Amsterdam, Munich, Germany

    Google Scholar 

  11. Grzegorzek M, Sav S, Izquierdo E, O’Connor NE (2010) Local Wavelet Features for Statistical Object Classification and Localisation. IEEE Multimedia 17 (1):56–66

    Article  Google Scholar 

  12. Hoffman J, Kulis B, Darrell T, Saenko K (2012) Discovering latent domains for multisource domain adaptation. In: Computer Vision–ECCV 2012, pp 702–715. Springer

  13. Jiang J, Zhai C (2007) Instance weighting for domain adaptation in nlp. In: ACL, vol 2007, pp 22

  14. Kulis B, Saenko K, Darrell T (2011) What you saw is not what you get: Domain adaptation using asymmetric kernel transforms. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1785–1792. IEEE

  15. Lai K, Bo L, Ren X, Fox D (2011) A large-scale hierarchical multi-view RGBD-D object dataset. In: 2011 IEEE international conference on robotics and automation (ICRA), pp 1817–1824. IEEE

  16. Lai K, Fox D (2009) 3d laser scan classification using web data and domain adaptation. In: Robotics: Science and Systems

  17. Leung T, Malik J (2001) Representing and recognizing the visual appearance of materials using three-dimensional textons. Int J Comput Vis 43(1):29–44

    Article  MATH  Google Scholar 

  18. Liu L, Shao L (2013) Learning discriminative representations from RGB-D video data. In: Proceedings of the Twenty-Third international joint conference on Artificial Intelligence, pp 1493–1500. AAAI Press

  19. Madry M, Song D, Kragic D (2011) 2D/3D Object Categorization for Task Based Grasping. In: European Robotics Forum 2011: RGB-D Workshop on 3D Perception in Robotics. Extended abstract

  20. Malisiewicz T, Efros AA (2008) Recognition by association via learning per-exemplar distances. In: IEEE conference on computer vision and pattern recognition, CVPR 2008, pp 1–8. IEEE

  21. Marton ZC, Seidel F, Balint-Benczedi F, Beetz M (2012) Ensembles of Strong Learners for Multi-cue Classification. Pattern Recognition Letters (PRL), Special Issue on Scene Understandings and Behaviours Analysis

  22. Richtsfeld A, Mörwald T, Prankl J, Zillich M, Vincze M. (2014) Learning of perceptual grouping for object segmentation on RGB-D data. J Vis Commun Image Represent 25(1):64–73

    Article  Google Scholar 

  23. Roark B, Bacchiani M (2003) Supervised and unsupervised pcfg adaptation to novel domains. In: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1, pp 126–133. Association for Computational Linguistics

  24. Rusu RB, Blodow N, Marton ZC, Beetz M (2008) Aligning Point Cloud Views using Persistent Feature Histograms. In: Proceedings of the 21st IEEE/RSJ international conference on intelligent robots and systems (IROS), Nice, France

  25. Rusu RB, Bradski G, Thibaux R, Hsu J (2010) Fast 3D recognition and pose using the Viewpoint Feature Histogram. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp 2155–2162, doi:10.1109/IROS.2010.5651280, (to appear in print)

  26. Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: Computer Vision–ECCV 2010, pp 213–226. Springer

  27. Shirahama K, Grzegorzek M (2014) Towards Large-Scale Multimedia Retrieval Enriched by Knowledge about Human Interpretation - Retrospective Survey. Multimedia Tools and Applications

  28. Spinello L, Arras KO (2012) Leveraging RGB-D data: Adaptive fusion and domain adaptation for object detection. In: 2012 IEEE international conference on robotics and automation (ICRA), pp 4469–4474.IEEE

  29. Wahl E, Hillenbrand U, Hirzinger G (2003) Surflet-Pair-Relation Histograms: A Statistical 3D-Shape Representation for Rapid Classification. In: 3D-Digital Imaging and Modeling (3DIM). Banff, Canada

  30. Yang J, Yan R, Hauptmann AG (2007) Cross-domain video concept detection using adaptive svms. In: Proceedings of the 15th international conference on Multimedia, pp 188–197. ACM

Download references

Author information

Authors and Affiliations

  1. Pattern Recognition Group, University of Siegen, Hoelderlinstrasse 3, 57076, Siegen, Germany

    Jorge René Nuricumbo & Marcin Grzegorzek

  2. DLR (German Aerospace Center), Institute of Robotics and Mechatronics (RM), Muenchner Strasse 20, 82234, Oberpfaffenhofen-Wessling, Germany

    Haider Ali & Zoltán-Csaba Márton

Authors
  1. Jorge René Nuricumbo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Haider Ali
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zoltán-Csaba Márton
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Marcin Grzegorzek
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marcin Grzegorzek.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nuricumbo, J.R., Ali, H., Márton, ZC. et al. Improving object classification robustness in RGB-D using adaptive SVMs. Multimed Tools Appl 75, 6829–6847 (2016). https://doi.org/10.1007/s11042-015-2612-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-015-2612-7

Keywords

Search

Navigation