Advertisement

International Journal of Computer Vision

, Volume 111, Issue 3, pp 345–364 | Cite as

Mapping Appearance Descriptors on 3D Body Models for People Re-identification

  • Davide Baltieri
  • Roberto Vezzani
  • Rita Cucchiara
Article

Abstract

People Re-identification aims at associating multiple instances of a person’s appearance acquired from different points of view, different cameras, or after a spatial or a limited temporal gap to the same identifier. The basic hypothesis is that the person’s appearance is mostly constant. Many appearance descriptors have been adopted in the past, but they are often subject to severe perspective and view-point issues. In this paper, we propose a complete re-identification framework which exploits non-articulated 3D body models to spatially map appearance descriptors (color and gradient histograms) into the vertices of a regularly sampled 3D body surface. The matching and the shot integration steps are directly handled in the 3D body model, reducing the effects of occlusions, partial views or pose changes, which normally afflict 2D descriptors. A fast and effective model to image alignment is also proposed. It allows operation on common surveillance cameras or image collections. A comprehensive experimental evaluation is presented using the benchmark suite 3DPeS.

Keywords

People re-identification 3D human model SARC3D 3D appearance model 

References

  1. Albu, A., Laurendeau, D., Comtois, S., Ouellet, D., Hebert, P., Zaccarin, A., Parizeau, M., Bergevin, R., Maldague, X., Drouin, R., Drouin, S., Martel-Brisson, N., Jean, F., Torresan, H., Gagnon, L., & Laliberte, F. (2006). MONNET: Monitoring pedestrians with a network of loosely-coupled cameras. In Proceedings of ICPR (pp. 924–928), IEEE.Google Scholar
  2. Andriluka, M., Roth, S., & Schiele, B. (2010). Monocular 3d pose estimation and tracking by detection. In CVPR, pp. 623–630.Google Scholar
  3. Andriluka, M., Roth, S., & Schiele, B. (2010). Monocular 3d pose estimation and tracking by detection. In Proceedings of CVPR (pp. 623–630).Google Scholar
  4. Bak, S., Corvee, E., Bremond, F., & Thonnat, M. (2010). Person re-identification using spatial covariance regions of human body parts. In Proceedings of AVSS (pp. 435–440).Google Scholar
  5. Baltieri, D., Vezzani, R., & Cucchiara, R. (2010). 3d body model construction and matching for real time people re-identification. In Proceedings of eurographics Italian chapter conference 2010 (EG-IT 2010), Genova, Italy.Google Scholar
  6. Baltieri, D., Vezzani, R., & Cucchiara, R. (2011). 3dpes: 3d people dataset for surveillance and forensics. In Proceedings of the 1st international ACM workshop on multimedia access to 3D human objects (pp. 59–64), Scottsdale, Arizona, USA.Google Scholar
  7. Baltieri, D., Vezzani, R., & Cucchiara, R. (2011). Sarc3d: A new 3d body model for people tracking and re-identification. In Proceedings of IEEE international conference on image analysis and processing (pp. 197–206), Ravenna, Italy.Google Scholar
  8. Baltieri, D., Vezzani, R., & Cucchiara, R. (2012). People orientation recognition by mixtures of wrapped distributions on random trees. In Proceedings of the 12th European conference on computer vision, Firenze, Italy.Google Scholar
  9. Barbosa, I. B., Cristani, M., Bue, A. D., Bazzani, L., & Murino, V. (2012). Re-identification with rgb-d sensors. In A. Fusiello, V. Murino, & R. Cucchiara (Eds.), ECCV Workshops (1). Lecture Notes in Computer Science (Vol. 7583, pp. 433–442). Springer.Google Scholar
  10. Bird, N., Masoud, O., Papanikolopoulos, N., & Isaacs, A. (2005). Detection of loitering individuals in public transportation areas. IEEE Transactions on Intelligent Transportation Systems, 6, 167–177.CrossRefGoogle Scholar
  11. Bk, S., Corve, E., Brmond, F., & Thonnat, M. (2012). Boosted human re-identification using riemannian manifolds. Image and Vision Computing, 30, 443–452.CrossRefGoogle Scholar
  12. Cai, Q., & Aggarwal, J. (1999). Tracking human motion in structured environments using a distributed-camera system. IEEE Transactions on Pattern Analysis and Machine Intelligence 21, 1241–1247.Google Scholar
  13. Calderara, S., Cucchiara, R., & Prati, A. (2008). Bayesian-competitive consistent labeling for people surveillance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 354–360.Google Scholar
  14. Colombo, C., Del Bimbo, A., & Valli, A. (2008). A real-time full body tracking and humanoid animation system. Parallel Computing, 34, 718–726.CrossRefGoogle Scholar
  15. Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In Proceedings of CVPR (Vol 1, pp. 886–893). Washington, DC: IEEE Computer Society.Google Scholar
  16. Dikmen, M., Akbas, E., Huang, T. S., & Ahuja, N. (2011). Pedestrian recognition with a learned metric. In Proceedings of the 10th Asian conference on computer vision—Volume Part IV. ACCV’10 (pp. 501–512). Berlin: Springer.Google Scholar
  17. Doretto, G., Sebastian, T., Tu, P. H., & Rittscher, J. (2011). Appearance-based person reidentification in camera networks: problem overview and current approaches. Journal of Ambient Intelligence and Humanized Computing, 2, 127–151.CrossRefGoogle Scholar
  18. Enzweiler, M., & Gavrila, D. M. (2010). Integrated pedestrian classification and orientation estimation. In CVPR (pp. 982–989).Google Scholar
  19. Farenzena, M., Bazzani, L., Perina, A., Murino, V., & Cristani, M. (2010). Person re-identification by symmetry-driven accumulation of local features. In Proceedings of CVPR (pp. 2360–2367).Google Scholar
  20. Gandhi, T., & Trivedi, M. (2006). Panoramic Appearance Map (PAM) for multi-camera based person re-identification. In Proceedings of AVSS (pp. 78–78). IEEE.Google Scholar
  21. Gandhi, T., & Trivedi, M. M. (2007). Person tracking and reidentification: Introducing Panoramic Appearance Map (PAM) for feature representation. Machine Vision and Applications, 18, 207–220.CrossRefzbMATHGoogle Scholar
  22. Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63, 3–42.CrossRefzbMATHGoogle Scholar
  23. Gijsenij, A., Gevers, T., & van de Weijer, J. (2011). Computational color constancy: Survey and experiments. IEEE Transactions on Image Processing, 20, 2475–2489.CrossRefMathSciNetGoogle Scholar
  24. Gilbert, A., & Bowden, R. (2006). Tracking objects across cameras by incrementally learning inter-camera colour calibration and patterns of activity. In Proceedings of ECCV (pp. 125–136).Google Scholar
  25. Gong, S., Cristani, M., Yan, S., & Loy, C. (Eds.). (2014). Person re-identification. Advances in computer vision and pattern recognition (Vol. XVIII). London: Springer.Google Scholar
  26. Grana, C., Vezzani, R., & Cucchiara, R. (2007). Enhancing hsv histograms with achromatic points detection for video retrieval. Proceedings of the ACM International Conference on Image and Video Retrieval, CIVR, 2007, 302–308.CrossRefGoogle Scholar
  27. Gray, D., & Tao, H. (2008). Viewpoint invariant pedestrian recognition with an ensemble of localized features. In Proceedings of ECCV, Berlin: Springer (pp. 262–275).Google Scholar
  28. Gray, D., Brennan, S., & Tao, H. (2007). Evaluating appearance models for recognition, reacquisition, and tracking. In Proceedings of 10th IEEE international workshop on performance evaluation of tracking and surveillance (PETS).Google Scholar
  29. Gualdi, G., Prati, A., & Cucchiara, R. (2010). Multi-stage sampling with boosting cascades for pedestrian detection in images and videos. In Proceedings of ECCV, Crete, Greece, pp. 196–209. Google Scholar
  30. Hartley, R. I., & Zisserman, A. (2004). Multiple view geometry in computer vision (2nd ed.) Cambridge University Press, ISBN: 0521540518.Google Scholar
  31. Hellinger, E. (1909). Neue begrndung der theorie quadratischer formen von unendlichvielen vernderlichen. Journal für die Reine und Angewandte Mathematik, 136, 210–271.Google Scholar
  32. Hirzer, M., Roth, P. M., Köstinger, M., & Bischof, H. (2012). Relaxed pairwise learned metric for person re-identification. In A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, & C. Schmid (Eds.), Computer Vision—ECCV 2012. Lecture Notes in Computer Science (Vol. 7577, pp. 780–793). Springer.Google Scholar
  33. Javed, O., & Shafique, K. (2005). Appearance modeling for tracking in multiple non-overlapping cameras. In Proceedings of CVPR (pp. 26–33). IEEE.Google Scholar
  34. Jungling, K., & Arens, M. (2011). View-invariant person re-identification with an implicit shape model. In Proceedings of AVSS (pp. 197–202).Google Scholar
  35. Kotoulas, L., & Andreadis, I. (2003). Colour histogram content-based image retrieval and hardware implementation. IEE Proceedings on Circuits, Devices and Systems, 150, 387–93.CrossRefGoogle Scholar
  36. Krumm, J., Harris, S., Meyers, B., Brumitt, B., Hale, M., & Shafer, S. (2000). Multi-camera multi-person tracking for EasyLiving. In Proceedings of third IEEE International workshop on visual surveillance (pp. 3–10). IEEE Comput. Soc.Google Scholar
  37. Monari, E., Maerker, J., & Kroschel, K. (2009). A robust and efficient approach for human tracking in multi-camera systems. In Proceedings of AVSS (pp. 134–139). IEEE.Google Scholar
  38. Nilski, A. (2008). Evaluating multiple camera tracking systems—The i-lids 5th scenario. In 42nd annual IEEE international carnahan conference on security technology, 2008. ICCST 2008 (pp. 277–279).Google Scholar
  39. Porikli, F. (2003). Inter-camera color calibration by correlation model function. In Proceedings of ICIP (Vols. 2, 3, pp. 133–136).Google Scholar
  40. Roullot, E. (2008). A unifying framework for color image calibration. 15th international conference on systems, signals and image processing, 2008. IWSSIP 2008 (pp. 97–100).Google Scholar
  41. Schügerl, P., Sorschag, R., Bailer, W., & Thallinger, G. (2007). Object re-detection using SIFT and MPEG-7 color descriptors. Lecture Notes in Computer Science, pp. 305–314.Google Scholar
  42. Schwartz, W., & Davis, L. (2009). Learning discriminative appearance-based models using partial least squares. In Proceedings of the XXII Brazilian symposium on computer graphics and image processing.Google Scholar
  43. Vezzani, R., & Cucchiara, R. (2010). Video surveillance online repository (visor): An integrated framework. Multimedia Tools and Applications, 50, 359–380.CrossRefGoogle Scholar
  44. Vezzani, R., & Cucchiara, R. (2014). In Benchmarking for person re-identification (pp. 333–349). London: Springer.Google Scholar
  45. Vezzani, R., Baltieri, D., & Cucchiara, R. (2014). People re-identification in surveillance and forensics: A survey. ACM Computing Surveys, 46, 29:1–29:3.Google Scholar
  46. Vezzani, R., Grana, C., & Cucchiara, R. (2011). Probabilistic people tracking with appearance models and occlusion classification: The ad-hoc system. Pattern Recognition Letters, 32, 867–877.CrossRefGoogle Scholar
  47. Zheng, W. S., Gong, S., & Xiang, T. (2011). Person re-identification by probabilistic relative distance comparison. In Proceedings of CVPR (pp. 649–656).Google Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Davide Baltieri
    • 1
  • Roberto Vezzani
    • 1
  • Rita Cucchiara
    • 1
  1. 1.Dipartimento di Ingegneria Enzo Ferrari-University of Modena and Reggio EmiliaModenaItaly

Personalised recommendations