People Re-identification using Deep Convolutional Neural Network

Guanwen Zhang, Jien Kato, Yu Wang, Kenji Mase

Abstract

One key issue for people re-identification is to find good features or representation to bridge the gaps among different appearances of the same people, which is introduced by large variances in view point, illumination and non-rigid deformation. In this paper, we create a deep convolutional neural network (deep CNN) to solve this problem and integrate feature learning and re-identification into one framework. In order to deal with such ranking-like comparison problem, we introduce a linear support vector machine (linear SVM) to replace conventional softmax activation function. Instead of learning cross-entropy loss, we adopt a margin-based loss of pair-wise image to measure the similarity of the comparing pair. Although the proposed model is quite simple, the experimental result shows encouraging performance of our method.

References

  1. Bazzani, L., Cristani, M., Perina, A., and Murino, V. (2012). Multiple-shot Person Re-identification by Chromatic and Epitomic Analyses, volume 33.
  2. Cheng, D. S., Cristani, M., Stoppa, M., Bazzani, L., and Murino, V. (2011). Custom Pictorial Structures for Re-identification.
  3. Dikmen, M., Akbas, E., Huang, T. S., and Ahuja, N. (2010). Pedestrian Recognition with a Learned Metric. Proc. Asia Conf. Computer Vision, pages 501-512.
  4. Ess, A., Leibe, B., and van Gool, L. (2007). Depth and Appearance for Mobile Scene Analysis. Proc. Int'l Conf. Computer Vision, pages 1-8.
  5. Farenzena, M., Bazzani, L., Perina, A., Murino, V., and Cristani, M. (2010). Person Re-Identification by Symmetry-Driven Accumulation of Local Features.
  6. Gray, D., Brennan, S., and Tao, H. (2007). Evaluating appearance models for recognition, reacquisition, and tracking. In 10th IEEE Int'l Workshop on Performance Evaluation of Tracking and Surveillance.
  7. Gray, D. and Tao, H. (2008). Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features. Proc. European Conf. Computer Vision, pages 262- 275.
  8. Hinton, G. E. and Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks, volume 313.
  9. Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. (2012). Improving neural networks by preventing co-adaptation of feature detectors, volume abs/1207.0580.
  10. Hirzer, M., Beleznai, C., Roth, P. M., and Bischof, H. (2011). Person re-identification by descriptive and discriminative classification. Proc. Scandinavian Conf. on Image Analysis.
  11. Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Proc. Advances in Neural Information Processing Systems 25, pages 1106-1114.
  12. Kviatkovsky, I., Adam, A., and Rivlin, E. (2013). Color Invariants for Person Reidentification, volume 35.
  13. LeCun, Y., Kavukcuoglu, K., and Farabet, C. (2010). Convolutional networks and applications in vision. pages 253-256.
  14. Li, W. and Wang, X. (2013). Locally Aligned Feature Transforma accros Views.
  15. Nagi, J., Di Caro, G. A., Giusti, A., , Nagi, F., and Gambardella, L. (2012). Convolutional Neural Support Vector Machines: Hybrid visual pattern classifiers for multi-robot systems. pages 27-34.
  16. Schwartz, W. R. and Davis, L. S. (2009). Learning Discriminative Appearance-Based Models Using Partial Least Squares. Proc. 2009 XXII Brazilian Symposium on Computer Graphics and Image Processing, pages 322-329.
  17. Sermanet, P., Kavukcuoglu, K., Chintala, S., and LeCun, Y. (2012). Pedestrian Detection with Unsupervised Multi-Stage Feature Learning, volume abs/1212.0142.
  18. Tang, Y. (2013). Deep Learning using Support Vector Machines, volume abs/1306.0239.
  19. Wang, X., Doretto, G., Sebastian, T., Rittscher, J., and Tu, P. (2007). Shape and Appearance Context Modeling. Proc. Int'l Conf. Computer Vision, pages 1-8.
  20. Zhang, G., Wang, Y., Kato, J., Marutani, T., and Mase, K. (2012). Local Distance Comparison for Multiple-shot People Re-identification. Proc. Asia Conf. Computer Vision, pages 677-690.
  21. Zhao, R., Ouyang, W., and Wang, X. (2013). Unsupervised Salience Learning for Person Re-identification.
  22. Zheng, W.-S., Gong, S., and Xiang, T. (2013). Reidentification by Relative Distance Comparison, volume 99.
  23. Zhong, S., , Zhong, S., and Ghosh, J. (2000). Decision Boundary Focused Neural Network Classifier.
Download


Paper Citation


in Harvard Style

Zhang G., Kato J., Wang Y. and Mase K. (2014). People Re-identification using Deep Convolutional Neural Network . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 216-223. DOI: 10.5220/0004740302160223


in Bibtex Style

@conference{visapp14,
author={Guanwen Zhang and Jien Kato and Yu Wang and Kenji Mase},
title={People Re-identification using Deep Convolutional Neural Network},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={216-223},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004740302160223},
isbn={978-989-758-009-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - People Re-identification using Deep Convolutional Neural Network
SN - 978-989-758-009-3
AU - Zhang G.
AU - Kato J.
AU - Wang Y.
AU - Mase K.
PY - 2014
SP - 216
EP - 223
DO - 10.5220/0004740302160223