Incremental object matching and detection with Bayesian methods and particle filters

Access Full Text

Incremental object matching and detection with Bayesian methods and particle filters

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Add to cart
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)
Add to cart

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

© The Institution of Engineering and Technology
Published

This study is about object matching, that is, a problem of locating the corresponding points of an object in an image. Conventional approaches to object matching are batch methods, meaning that the methods first learn the object model from a training set of example images that contain instances of the object, and then use the learned object model to match instances of the same object (or object class) in unseen test images. Such batch learning often leads to computationally heavy learning, at least when the images are incorporated sequentially into the system and large memory requirements. In computer vision, little work has been done in developing incremental object learners. Especially, an incremental object-matching method has – to the best knowledge of the authors – never been introduced. In this paper, the authors present such a method. Our technique finds the corresponding points of similar object instances, appearing in natural greyscale images with arbitrary location, scale and orientation, by processing the images sequentially. The approach is Bayesian and combines the shape and appearance of the corresponding points into the posterior distribution for the location of them. The posterior distribution is recursively sampled with particle filters to locate the most probable corresponding point sets in the image being processed. The results indicate that the matched corresponding points can be used in forming a representation of the object with which instances of the object in novel test images are successfully detected.

Inspec keywords: particle filtering (numerical methods); image representation; object detection; Bayes methods; image colour analysis; computer vision; learning (artificial intelligence); image matching

Other keywords: object class; object detection; point set; incremental object matching; object representation; batch method; posterior distribution; batch learning; particle filter; natural greyscale image; object model; computer vision; image processing; Bayesian method

Subjects: Optical, image and video signal processing; Computer vision and image processing techniques; Other topics in statistics; Interpolation and function approximation (numerical analysis); Filtering methods in signal processing; Knowledge engineering techniques; Interpolation and function approximation (numerical analysis); Other topics in statistics

References

    1. 1)
      • Kamarainen, J., Hamouz, M., Kittler, J., Paalanen, P., Ilonen, J., Drobchenko, A.: `Object localisation using generative probability model for spatial constellation and local image features', Proc. ICCV, 2007, p. 1–8.
    2. 2)
      • Weber, M., Welling, M., Perona, P.: `Unsupervised learning of models for recognition', Proc. ECCV, 2000, p. 18–32.
    3. 3)
      • Y. Bar-Shalom , X.R. Li . (1995) Multitarget–multisensor tracking: principles and techniques.
    4. 4)
      • Fei-Fei, L., Fergus, R., Perona, P.: `A Bayesian approach to unsupervised one-shot learning of object categories', Proc. ICCV, 2003, p. 1134–1141.
    5. 5)
    6. 6)
      • Winn, J., Jojic, N.: `LOCUS: learning object classes with unsupervised segmentation', Proc. ICCV, 2005, 1, p. 756–763.
    7. 7)
      • A. Doucet , N. de Freitas , N. Gordon . (2001) Sequential Monte Carlo methods in practice.
    8. 8)
    9. 9)
    10. 10)
      • A. Gelman , J.B. Carlin , H.S. Stern , D.B. Rubin . (2004) Bayesian data analysis.
    11. 11)
      • Borenstein, E., Sharon, E., Ullman, S.: `Combining top-down and bottom-up segmentation', Proc. CVPR Workshop, 2004, p. 46–53.
    12. 12)
    13. 13)
    14. 14)
      • Amores, J., Sebe, N., Radeva, P.: `Fast spatial pattern discovery integrating boosting with constellations of contextual descriptors', Proc. CVPR, 2005, 2, p. 769–775.
    15. 15)
    16. 16)
    17. 17)
      • M.J.L. Orr . Introduction to radial basis function networks.
    18. 18)
    19. 19)
    20. 20)
      • Fergus, R., Perona, P., Zisserman, A.: `A sparse object category model for efficient learning and complete recognition', Toward category-level object recognition, p. 443–461, (LNCS, 4170) (Springer, 2007).
    21. 21)
    22. 22)
    23. 23)
      • M. Toivanen , J. Lampinen . Bayesian online learning of corresponding points of objects with sequential Monte Carlo. Int. J. Comput. Intell , 4 , 318 - 324
    24. 24)
      • Shotton, J., Blake, A., Cipolla, R.: `Contour-based learning for object detection', Proc. ICCV, 2005, 1, p. 503–510.
    25. 25)
      • J. Liu , R. Chen , T. Logvinenko , C.A. Doucet , J. de Freitas , N. Gordon . (2001) A theoretical framework for sequential importance sampling with resampling, Sequential Monte Carlo methods in practice.
    26. 26)
      • Willamowski, J., Arregui, D., Csurka, G., Dance, C.R., Fan, L.: `Categorizing nine visual classes using local appearance descriptors', ICPR Workshop on Learning for Adaptable Visual Systems, 2004, p. 21–31.
    27. 27)
      • Toivanen, M., Lampinen, J.: `Incremental Bayesian learning of feature points from natural images', Proc. CVPR Workshops, 2009, p. 39–46.
    28. 28)
      • Toivanen, M., Lampinen, J.: `Incremental object matching with Bayesian methods and particle filters', Proc. Digital Image Computing: techniques and Applications, 2009, p. 111–118.
    29. 29)
    30. 30)
    31. 31)
      • Mikolajczyk, K., Leibe, B., Schiele, B.: `Multiple object class detection with a generative model', Proc. CVPR, 2006, p. 26–36.
    32. 32)
      • Fergus, R., Perona, P., Zisserman, A.: `Object class recognition by unsupervised scale-invariant learning', Proc. CVPR, 2003, p. 264–271.
    33. 33)
      • Lazebnik, S., Schmid, C., Ponce, J.: `Semi-local affine parts for object recognition', Proc. BMVC, 2004, 2, p. 959–968.
    34. 34)
    35. 35)
      • Wolf, L., Martin, I.: `Robust boosting for learning from few examples', Proc. CVPR, 2005, p. 359–364.
    36. 36)
      • Ahuja, N., Todorovic, S.: `Learning the taxonomy and models of categories present in arbitrary images', Proc. ICCV;, 2007, p. 1–8.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2010.0030
Loading

Related content

content/journals/10.1049/iet-cvi.2010.0030
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading