OBJECT RECOGNITION IN PROBABILISTIC 3-D VOLUMETRIC SCENES

Maria I. Restrepo, Brandon A. Mayer, Joseph L. Mundy

2012

Abstract

A new representation of 3-d object appearance from video sequences has been developed over the past several years (Pollard and Mundy, 2007; Pollard, 2008; Crispell, 2010), which combines the ideas of background modeling and volumetric multi-view reconstruction. In this representation, Gaussian mixture models for intensity or color are stored in volumetric units. This 3-d probabilistic volume model, PVM, is learned from a video sequence by an on-line Bayesian updating algorithm. To date, the PVM representation has been applied to video image registration (Crispell et al., 2008), change detection (Pollard and Mundy, 2007) and classification of changes as vehicles in 2-d only (Mundy and Ozcanli, 2009; O¨ zcanli and Mundy, 2010). In this paper, the PVM is used to develop novel viewpoint-independent features of object appearance directly in 3-d. The resulting description is then used in a bag-of-features classification algorithm to recognize buildings, houses, parked cars, parked aircraft and parking lots in aerial scenes collected over Providence, Rhode Island, USA. Two approaches to feature description are described and compared: 1) features derived from a PCA analysis of model neighborhoods; and 2) features derived from the coefficients of a 3-d Taylor series expansion within each neighborhood. It is shown that both feature types explain the data with similar accuracy. Finally, the effectiveness of both feature types for recognition is compared for the different categories. Encouraging experimental results demonstrate the descriptive power of the PVM representation for object recognition tasks, promising successful extension to more complex recognition systems.

References

  1. Bariya, P. and Nishino, K. (2010). Scale-Hierarchical 3D Object Recognition in Cluttered Scenes. IEEE Conference on Computer Vision and Pattern Recognition.
  2. Bradley, P. S. and Fayyad, U. M. (1998). Refining Initial Points for K-Means Clustering. In Proceedings of the 15th International Conference on Machine Learning.
  3. Bronstein, A. M., Broinstein, M. M., Guibas, L. J., and Ovsjanikov, M. (2011). Shape Google: Geometric Words and Expressions for Invariant Shape Retrieval. ACM Transactions on Graphics.
  4. Chan, T. F., Golub, G. H., and LeVeque, R. J. (1979). Updating Formulae and a Pairwise Algorithm for Computing Sample Variances. Technical report, Department of Computer Science. Stanford University.
  5. Crispell, D., Mundy, J., and Taubin, G. (2008). ParallaxFree Registration of Aerial Video. In BMVC.
  6. Crispell, D. E. (2010). A Continuous Probabilistic Scene Model for Aerial Imagery. PhD thesis, School of Engineering, Brown University.
  7. Csurka, G., Dance, C. R., Fan, L., Willamowski, J., and Bray, C. (2004). Visual categorization with bags of keypoints. In In Workshop on Statistical Learning in Computer Vision, ECCV.
  8. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In IEEE Conference on Computer Vision and Pattern Recognition.
  9. Drost, B., Ulrich, M., Navab, N., and Ilic, S. (2010). Model Globally, Match Locally: Efficient and Robust 3D Object Recognition. IEEE Conference on Computer Vision and Pattern Recognition.
  10. Elkan, C. (2003). Using the triangle inequality to accelerate k-means. In Proceedings of the Twentieth International Conference on Machine Learning.
  11. Felzenszwalb, P., McAllester, D., and Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In IEEE Conference on Computer Vision and Pattern Recognition.
  12. Fergus, R., Perona, P., and Zisserman, A. (2003). Object class recognition by unsupervised scale-invariant learning. In IEEE Conference on Computer Vision and Pattern Recognition.
  13. Freeman, W. and Adelson, E. (1991). The design and use of steerable filters. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  14. Gupta, P., Arrabolu, S., Brown, M., and Savarese, S. (2009). Video scene categorization by 3D hierarchical histogram matching. In International Conference on Computer Vision.
  15. Hamerly, G. and Elkan, C. (2003). Learning the k in kmeans. In Seventeenth annual conference on neural information processing systems (NIPS).
  16. Harris, C. and Stephens, M. (1988). A combined corner and edge detector. Alvey vision conference.
  17. Joachims, T. (1997). Text Categorization with Support Vector Machines: Learning with Many Relevant Features. In ECML.
  18. Judd, D., McKinley, P., and Jain, A. (1998). Large-scale parallel data clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  19. Leung, T. and Malik, J. (1999). Recognizing surfaces using three-dimensional texton. In Proceedings of the Seventh IEEE International Conference on Computer Vision.
  20. Lowe, D. G. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision.
  21. Maitra, R., Peterson, A. D., and Ghosh, A. P. (2010). A systematic evaluation of different methods for initializing the K-means clustering algorithm. In IEEE Transactions of Knowledge and Data Engineering.
  22. Miller, A., Jain, V., and Mundy, J. (2011). Real-time Rendering and Dynamic Updating of 3-d Volumetric Data. In Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units.
  23. Mundy, J. L. and Ozcanli, O. C. (2009). Uncertain geometry: a new approach to modeling for recognition. In 2009 SPIE Defense, Security and Sensing Conference.
  24. O zcanli, O. and Mundy, J. (2010). Vehicle Recognition as Changes in Satellite Imagery. In International Conference on Pattern Recognition.
  25. Papadakis, P., Pratikakis, I., and Theoharis, T. (2010). PANORAMA: A 3D Shape Descriptor Based on Panoramic Views for Unsupervised 3D Object Retrieval. International Journal of Computer Vision.
  26. Pelleg, D. and Moore, A. (2000). X-means: Extending Kmeans with E cient Estimation of the Number of Clusters. In International Conference on Machine Learning.
  27. Pollard, T. (2008). Comprehensive 3-d Change Detection Using Volumetric Appearance Modeling. PhD thesis, Division of Applied Mathematics, Brown University.
  28. Pollard, T. and Mundy, J. (2007). Change Detection in a 3-d World. In IEEE Conference on Computer Vision and Pattern Recognition.
  29. Raviv, D., Bronstein, M. M., Bronstein, A. M., and Kimmel, R. (2010). Volumetric heat kernel signatures. In 3DOR 7810: Proceedings of the ACM workshop on 3D object retrieval.
  30. Shapira, L., Shalom, S., Shamir, A., Cohen-Or, D., and Zhang, H. (2010). Contextual Part Analogies in 3D Objects. International Journal of Computer Vision.
  31. Sipiran, I. and Bustos, B. (2010). A Robust 3D Interest Points Detector Based on Harris Operator. In Eurographics Workshop on 3D Object Retrieval.
  32. Sivic, J., Russell, B., Efros, A., Zisserman, A., and Freeman, W. (2005). Discovering objects and their location in images. In International Conference on Computer Vision.
  33. Snavely, N. and Seitz, S. (2006). Photo tourism: exploring photo collections in 3D. ACM Transactions on Graphics.
  34. Thomas, A., Ferrar, V., Leibe, B., Tuytelaars, T., Schiel, B., and Van Gool, L. (2006). Towards Multi-View Object Class Detection. In IEEE Conference on Computer Vision and Pattern Recognition.
  35. Varma, M. and Zisserman, A. (2009). A Statistical Approach to Material Classification Using Image Patch Exemplars. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  36. Zhang, J., Marszalek, M., Lazebnik, S., and Schmid, C. (2007). Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study. Int. J. Comput. Vision.
Download


Paper Citation


in Harvard Style

I. Restrepo M., A. Mayer B. and L. Mundy J. (2012). OBJECT RECOGNITION IN PROBABILISTIC 3-D VOLUMETRIC SCENES . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-8425-99-7, pages 180-190. DOI: 10.5220/0003776301800190


in Bibtex Style

@conference{icpram12,
author={Maria I. Restrepo and Brandon A. Mayer and Joseph L. Mundy},
title={OBJECT RECOGNITION IN PROBABILISTIC 3-D VOLUMETRIC SCENES},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},
year={2012},
pages={180-190},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003776301800190},
isbn={978-989-8425-99-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - OBJECT RECOGNITION IN PROBABILISTIC 3-D VOLUMETRIC SCENES
SN - 978-989-8425-99-7
AU - I. Restrepo M.
AU - A. Mayer B.
AU - L. Mundy J.
PY - 2012
SP - 180
EP - 190
DO - 10.5220/0003776301800190