Regional SVM Classifiers with a Spatial Model for Object Detection

Zhu Teng, Baopeng Zhang, Onecue Kim, Dong-Joong Kang

Abstract

This paper presents regional Support Vector Machine (SVM) classifiers with a spatial model for object detection. The conventional SVM maps all the features of training examples into a feature space, treats these features individually, and ignores the spatial relationship of the features. The regional SVMs with a spatial model we propose in this paper take into account a 3-dimentional relationship of features. One-dimensional relationship is incorporated into the regional SVMs. The other two-dimensional relationship is the pairwise relationship of regional SVM classifiers acting on features, and is modelled by a simple conditional random field (CRF). The object detection system based on the regional SVM classifiers with the spatial model is demonstrated on several public datasets, and the performance is compared with that of other object detection algorithms.

References

  1. Moore, R., Lopes, J., 1999. Paper templates. In TEMPLATE'06, 1st International Conference on Template Production. SciTePress.
  2. Smith, J., 1998. The book, The publishing company. London, 2nd edition.
  3. Bernhard Scholkopf, Alexander J. Smola, 2002. Learning with kernels: Support Vector Machines, Regularization, Optimization, and Beyond, The MIT Press.
  4. Andreas Opelt, Axel Pinz, Andrew Zisserman, 2006. Incremental learning of object detectors using a visual shape alphabe, In Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 3-10.
  5. Zheng Song, Qiang Chen, Zhongyang Huang, Yang Hua, Shuicheng Yan, 2011. Contextualizing Object Detection and Classification, In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR).
  6. Tagare H., Vos F., Jaffe C.C., Duncan J.S., 1995. Arrangement: A spatial relation between parts for evaluating similarity of tomographic section, In IEEE Trans. PAMI, 17 (9), 880-893.
  7. Bogdan Alexe, Thomas Deselaers, Vittorio Ferrari, 2010. What is an object? In Proc. CVPR.
  8. Martin A. Fischler, Robert A. Elschlager, 1973. The representation and matching of pictorial structures, In IEEE Transactions on Computers, Vol. c-22, No. 1.
  9. Long (Leo) Zhu, Yuanhao Chen, Alan Yuille, William Freeman, 2010. Latent Hierarchical Structural Learning for Object Detection, In Proc. IEEE Computer Vision and Pattern Recognition (CVPR).
  10. Sanjiv Kumar, Martial Hebert, 2006. Discriminative random fields: A discriminative framework for contextual interaction in classification, In Int. J. Comput. Vis., vol. 68, no. 2, pp.179 -201.
  11. David J. Crandall and Daniel P. Huttenlocher, 2006. Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition, In Proc. ECCV, pages I: 16-29.
  12. David Crandall, Pedro Felzenszwalb, Daniel Huttenlocher, 2005. Spatial Priors for Part-Based Recognition using Statistical Models, In Proc. IEEE Conf. Computer Vision and Pattern Recognition.
  13. Navneet Dalal and Bill Triggs, 2005. Histograms of Oriented Gradients for Human Detection, In Proc. IEEE Conf. Computer Vision and Pattern Recognition.
  14. T. Ojala, M. Pietikäinen, and D. Harwood, 1996. A Comparative Study of Texture Measures with Classification Based on Feature Distributions, In Pattern Recognition, vol. 29, pp. 51-59.
  15. Daphne Koller, Nir Friedman, 2009. Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning, The MIT Press.
  16. Pedro F. Felzenszwalb, Ross B. Girshick, David McAllester, and Deva Ramanan, 2010. Object Detection with Discriminatively Trained Part-Based Models, In IEEE Trans. PAMI, Vol. 32, No. 9.
  17. P. Felzenszwalb, D. McAllester, and D. Ramanan, 2008. A Discriminatively Trained, Multiscale, Deformable Part Model, In Proc. IEEE Conf. Computer Vision and Pattern Recognition.
  18. C.-C. Chang and C.-J. Lin, 2011. LIBSVM : a library for support vector machines, In ACM Transactions on Intelligent Systems and Technology, 2:27:1--27:27. Software available at http://www.csie.ntu.edu.tw/ cjlin/libsvm.
  19. Chih-Wei Hsu, Chih-Chung Chang, and Chih-Jen Lin, 2003. A Practical Guide to Support Vector Classification, Technical Report, Taipei.
  20. M. Everingham, A. Zisserman, C.K.I., Williams and L. Van Gool, 2007. The PASCAL Visual Object Classes Challenge 2007 (VOC 2007) Results. Available at: http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc20 07/.
  21. Shivani Agarwal, Aatif Awan, and Dan Roth, 2004. Learning to detect objects in images via a sparse, partbased representation, In IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(11):1475-1490.
Download


Paper Citation


in Harvard Style

Teng Z., Zhang B., Kim O. and Kang D. (2014). Regional SVM Classifiers with a Spatial Model for Object Detection . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 372-379. DOI: 10.5220/0004679003720379


in Bibtex Style

@conference{visapp14,
author={Zhu Teng and Baopeng Zhang and Onecue Kim and Dong-Joong Kang},
title={Regional SVM Classifiers with a Spatial Model for Object Detection},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={372-379},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004679003720379},
isbn={978-989-758-004-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Regional SVM Classifiers with a Spatial Model for Object Detection
SN - 978-989-758-004-8
AU - Teng Z.
AU - Zhang B.
AU - Kim O.
AU - Kang D.
PY - 2014
SP - 372
EP - 379
DO - 10.5220/0004679003720379