Skip to main content
SpringerLink
Log in

Real-time Object Recognition in Sparse Range Images Using Error Surface Embedding

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

A novel object recognition algorithm is introduced to identify objects and recover their pose from sparse range data. The method is based upon comparing the 7-D error surfaces of objects in various poses, which result from the registration error function between two convolved surfaces. The objects and their pose values are encoded by a small set of feature vectors extracted from the minima of the error surfaces. The problem of object recognition is thus reduced to comparing these feature vectors to find the corresponding error surfaces between the runtime data and a preprocessed database.

The algorithm, called Potential Well Space Embedding (PWSE) has been implemented and tested on both simulated and real data. The experimental results show the technique to be both effective and efficient, executing at 122 frames per second on standard hardware and with recognition rates exceeding 97% for a database of 60 objects. The performance of PWSE on the large size database was also evaluated on the Princeton Shape Benchmark containing 1,814 objects. In addition, it functions well with very sparse data, possibly comprising only hundreds of points per image, and is shown to be robust to measurement error and outliers.

With some small modifications, we applied PWSE to the problem of object class recognition. In experiments with the Princeton Shape Benchmark, PWSE is able to provides better classification rates than the previous methods in terms of nearest neighbour classification.

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

Similar content being viewed by others

References

  • Abraham, M., Jasiobedzki, P., & Umasuthan, M. (2001). Robust 3D vision for autonomous space robotic operations. In Proceedings of 6th international symposium of artificial intelligence and robotics in space (pp. 2235–2241).

  • Bondy, M., Taati, B., Jasiobedzki, P., & Greenspan, M. (2007). Variable dimensional local shape descriptors for object recognition in range data. In Proceedings of the international conference on computer vision—workshop on 3D representation for recognition (pp. 1–8).

  • Bentley, J. L. (1990). K-d trees for semidynamic point sets. In Proceedings of the sixth annual symposium on computational geometry (pp. 187–197). New York, NY, USA, 1990 New York: ACM. ISBN 0-89791-362-0.

    Chapter  Google Scholar 

  • Besl, P. J., & McKay, H. D. (1992). A method for registration of 3D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2), 239–256. ISSN 0162-8828.

    Article  Google Scholar 

  • Blais, G., & Levine, M. (1995). Registering multiview range data to create 3D computer objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(8), 820–824.

    Article  Google Scholar 

  • Campbell, R. J., & Flynn, P. J. (1999). Eigenshapes for 3D object recognition in range data. In Proceedings of IEEE computer society conference on computer vision and pattern recognition (Vol. 2, pp. 505–510).

  • Chua, C. S., & Jarvis, R. (1997). Point signatures: A new representation for 3D object recognition. International Journal of Computer Vision, 25(1), 63–85. ISSN 0920-5691.

    Article  Google Scholar 

  • Cyr, C. M., & Kimia, B. B. (2004). A similarity-based aspect-graph approach to 3D object recognition. International Journal of Computer Vision, 57(1), 5–22. ISSN 0920-5691.

    Article  Google Scholar 

  • Demartines, P., & Hérault, J. (1997). Curvilinear component analysis: A self-organizing neural network for nonlinear mapping of data sets. IEEE Transactions on Neural Networks, 8(1), 148–154.

    Article  Google Scholar 

  • Freund, Y., & Schapire, R. E. (1999). A brief introduction to boosting. In Proceedings of the sixteenth international joint conference on artificial intelligence (pp. 1401–1406). San Mateo: Morgan Kaufmann.

    Google Scholar 

  • Frome, A., Huber, D., Kolluri, R., Bulow, T., & Malik, J. (2004). Recognizing objects in range data using regional point descriptors. In Proceedings of the European conference on computer vision (pp. 224–237).

  • Godin, G., Rioux, M., & Baribeau, R. (1994). Three-dimensional registration using range and intensity information. In Proceedings of SPIE videometric III (Vol. 2350, pp. 279–290).

  • Hjaltason, G. R., & Samet, H. (2003). Properties of embedding methods for similarity searching in metric spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(5), 530–549.

    Article  Google Scholar 

  • Huttenlocher, D. P., Lilien, R. H., & Olson, C. F. (1999). View-based recognition using an eigenspace approximation to the Hausdorff measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(9), 951–955. ISSN 0162-8828.

    Article  Google Scholar 

  • Johnson, A. E., & Hebert, M. (1997). Surface registration by matching oriented points. In Proceedings of international conference on recent advances in 3D digital imaging and modeling (pp. 121–128).

  • Johnson, A. E., & Hebert, M. (1999). Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(5), 433–449. ISSN 0162-8828.

    Article  Google Scholar 

  • Jost, T. (2002). Fast geometric matching for shape registration. PhD thesis, University of Neuchâtel.

  • Low, K.-L., & Lastra, A. (2003). Reliable and rapidly-converging ICP algorithm using multiresolution smoothing. In Proceedings of fourth international conference on 3D digital imaging and modeling (pp. 171–178).

  • Low, K.-L., & Lastra, A. (2007). Predetermination of ICP registration errors and its application to view planning. In Proceedings of sixth international conference on 3D digital imaging and modeling (pp. 73–80).

  • Lowe, D. G. (1999). Object recognition from local scale-invariant features. In Proceedings of the seventh IEEE international conference on computer vision (Vol. 2, pp. 1150–1157).

  • Luck, J., Little, C., & Hoff, W. (2000). Registration of range data using a hybrid simulated annealing and iterative closest point algorithm. In Proceedings of IEEE international conference on robotics and automation (Vol. 4, pp. 3739–3744).

  • Mian, A. S., Bennamoun, M., & Owens, R. (2006). Three-dimensional model-based object recognition and segmentation in cluttered scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(10), 1584–1601.

    Article  Google Scholar 

  • Nene, S. A., & Nayar, S. K. (1997). A simple algorithm for nearest neighbor search in high dimensions. IEEETPAMI: IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(9), 989–1003.

    Article  Google Scholar 

  • Pope, A. R., & Lowe, D. G. (1993). Learning 3D object recognition models from 2d images. In Proceedings of AAAI fall workshop on machine learning in computer vision (pp. 35–39).

  • Pope, A. R., & Lowe, D. G. (2000). Probabilistic models of appearance for 3D object recognition. International Journal of Computer Vision, 40(2), 149–167. ISSN 0920-5691.

    Article  MATH  Google Scholar 

  • Quinn, J. M. (2003). Parallel programming in C with MPI and OpenMP. New York: McGraw-Hill. ISBN 0071232656.

    Google Scholar 

  • Rusinkiewicz, S., & Levoy, M. (2001). Efficient variants of the ICP algorithm. In Proceedings of fourth international conference on 3-D digital imaging and modeling (pp. 145–152).

  • Schiele, B., & Crowley, J. L. (1996) Probabilistic object recognition using multidimensional receptive field histograms. In Proceedings of the 13th international conference on pattern recognition (Vol. 2, pp. 50–54). Washington, DC, USA, 1996. Los Alamitos: IEEE Computer Society. ISBN 0-8186-7282-X.

    Chapter  Google Scholar 

  • Shan, Y., Matei, B., Sawhney, H. S., Kumar, R., Huber, D., & Hebert, M. (2004). Linear model hashing and batch RANSAC for rapid and accurate object recognition. In IEEE international conference on computer vision and pattern recognition (pp. 121–128).

  • Shang, L., & Greenspan, M. (2007). Pose determination by potentialwell space embedding. Sixth international conference on 3D digital imaging and modeling, 2007. 3DIM ’07 (pp. 297–304). ISSN 1550-6185.

  • Shang, L., Greenspan, M., & Jasiobedzki, P. (2007). Model-based tracking by classification in a tiny discrete pose space. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(6), 976–989. ISSN 0162-8828.

    Article  Google Scholar 

  • Shilane, P., Min, P., Kazhdan, M., & Funkhouser, T. (2004). The Princeton shape benchmark. In Proceedings of international conference on shape modeling and applications 2004 (pp. 167–178).

  • Simon, D. A. (1996). Fast and accurate shape-based registration. PhD thesis, Carnegie Mellon University.

  • Skocaj, D., & Leonardis, A. (2001). Robust recognition and pose determination of 3D objects using range images in eigenspace approach. In Proceedings of the third international conference on 3D digital imaging and modeling (pp. 171–178).

  • Sun, Y., Paik, J., Koschan, A., Page, D. L., & Abidi, M. A. (2003). Point fingerprint: A new 3D object representation scheme. IEEE Transactions on Systems, Man and Cybernetics, Part B, 33(4), 712–717. ISSN 1083-4419.

    Article  Google Scholar 

  • Turk, M. A., & Pentland, A. P. (1991). Face recognition using eigenfaces. In Proceedings IEEE computer society conference on computer vision and pattern recognition (pp. 586–591).

  • Wu, F. C., & Hu, Z. Y. (2006). The LLE and a linear mapping. Pattern Recognition, 39(9), 1799–1804.

    Article  MATH  Google Scholar 

  • Wu, Y., Huang, T. S., & Toyama, K. (2001). Self-supervised earning for object recognition based on kernel discriminant-em algorithm. IEEE International Conference on Computer Vision, 1, 275–280.

    Google Scholar 

  • Yamany, S. M., & Farag, A. A. (2002). Surface signatures: an orientation independent free-form surface representation scheme for the purpose of objects registration and matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(8), 1105–1120. ISSN 0162-8828.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical & Computer Engineering, Queen’s University, Kingston, Ontario, Canada

    Limin Shang

  2. Department of Electrical & Computer Engineering, School of Computing, Queen’s University, Kingston, Ontario, Canada

    Michael Greenspan

Authors
  1. Limin Shang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Michael Greenspan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Limin Shang.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Shang, L., Greenspan, M. Real-time Object Recognition in Sparse Range Images Using Error Surface Embedding. Int J Comput Vis 89, 211–228 (2010). https://doi.org/10.1007/s11263-009-0276-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-009-0276-3

Keywords

Search

Navigation