This study contributes in two ways to the research of multi-camera object tracking in the context of visual surveillance. Firstly, a semi-automatic scene calibration method is proposed to deal with mapping a network of cameras with overlapped fields of view onto a single ground plane view, even when the overlap is not substantial. The proposed method uses a semi-supervised approach that combines tracked blobs with user-selected line scene features to recover the homographies between camera views that are both simple and accurate. Then, based on the scene calibration information, the intersection points of the projected vertical axis of single camera blobs are used to make object correspondences across multiple views. The method works in mixed environments of both pedestrians and vehicles, and is shown to be accurate and robust against segmentation noise and occlusions. Finally, the advantage of the proposed method is demonstrated by quantitative tracking performance evaluation and comparison against previous methods.

References

1. 1)
  - 24. Available at http://www.cvlab.epfl.ch/data/pom, accessed July 2014.
2. 2)
  - 1. Hartley, R., Zisserman, A.: ‘Multiple view geometry in computer vision’ (Cambridge University Press, Cambridge, 2003, 2nd edn.).
3. 3)
  - 4. Zhang, Z., Scanlon, A.: ‘Video surveillance using a multi-camera tracking and fusion system’. IEEE Int. Workshop on Multi-camera and Multi-modal Sensor Fusion: Algorithms and Applications, Marseille, France, 2008, pp. 435–456.
4. 4)
  - 17. Borg, M., Thirde, D.J., Ferryman, J.M., et al: ‘Automated scene understanding for airport aprons’. The 18th Australian Joint Conf. on Artificial Intelligence (AI05) in Sydney, Australia, December, 2005, vol. 3809, pp. 593–603.
5. 5)
  - 14. Ben Shitrit, H., Berclaz, J., Fleuret, F., et al: ‘Tracking multiple people under global appearance constraints’, 2011 IEEE Int. Conf. on Computer Vision (ICCV), 2011, pp. 137–144.
6. 6)
  - 26. Available at http://www.mm.media.kyoto-u.ac.jp/datasets/shinpuhkan/index-e.html, accessed July 2014.
7. 7)
  - 28. Available at http://www.openvisor.org/3dpes.asp, accessed July 2014.
8. 8)
  - 22. Available at http://www.cvg.rdg.ac.uk/slides/pets.html, accessed March 2014.
9. 9)
  - 13. Orghidan, R., Salvi, J., Gordan, M., et al: ‘Camera calibration using two or three vanishing points’. Federated Conf. on IEEE Computer Science and Information Systems (FedCSIS), 2012, pp. 123–130.
10. 10)
  - M.A. Fischler , R.C. Bolles . Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM , 381 - 395
11. 11)
  - 6. Ellis, T., Makris, D., Black, J.: ‘Learning a multi-camera topology’. Joint IEEE Int. Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, Nice, France, 2003, pp. 165–171.
12. 12)
  - 21. Available at http://www.homepages.inf.ed.ac.uk/rbf/CAVIARDATA1/ accessed March 2014.
13. 13)
  - S. Khan , M. Shah . Consistent labeling of tracked objects in multiple cameras with overlapping fields of view. IEEE Trans. Pattern Anal. Machine Intell. , 10 , 1355 - 1360
14. 14)
  - 23. Available at http://www.cvpapers.com/datasets.html, accessed July 2014.
15. 15)
  - 27. Available at https://www.gov.uk/imagery-library-for-intelligent-detection-systems, accessed July 2014.
16. 16)
  - 29. Available at http://www.dipersec.king.ac.uk/MuCCD/, accessed June 2014.
17. 17)
  - 14. Wang, X.: ‘Intelligent multi-camera video surveillance: a review’, Pattern Recognit. Lett., 2013, 34, (1), pp. 3–19 (doi: 10.1016/j.patrec.2012.07.005).
18. 18)
  - 12. Li, B., Peng, K., Ying, X., Zha, H.: ‘Simultaneous vanishing point detection and camera calibration from single images’. ISVC’ 10, USA, 2010, pp. 151–160.
19. 19)
  - 19. Luo, X., Tan, R.T., Veltkamp, R.C.: ‘Multi-person tracking based on vertical reference lines and dynamic visibility analysis’. 18th IEEE Int. Conf. on Image Processing (ICIP), 2011, 2011, pp. 1877–1880.
20. 20)
  - 25. Available at http://www.wide-baseline-camera-network-contest.org/?page_id=35, accessed July 2014.
21. 21)
  - 30. Yin, F., Makris, D., Velastin, S.A.: ‘Performance evaluation of object tracking algorithms’. 10th IEEE Int. Workshop on Performance Evaluation of Tracking and Surveillance (PETS2007), Rio de Janeiro, Brazil, October 2007.
22. 22)
  - 31. Available at http://www.viper-toolkit.sourceforge.net/docs/gt/, accessed March 2014.
23. 23)
  - 17. Khan, S.M., Shah, M.: ‘Tracking multiple occluding people by localizing on multiple scene planes’, IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, (3), pp. 505–519 (doi: 10.1109/TPAMI.2008.102).
24. 24)
  - 9. Liu, J., Collins, R.T., Liu, Y.: ‘Surveillance camera autocalibration based on pedestrian height distributions’. British Machine Vision Conf. (BMVC), Dundee, 2011.
25. 25)
  - 7. Stauffer, C., Tieu, K.: ‘Automated multi-camera planar tracking correspondence modeling’. Proc. CVPR, 2003, vol. 1, pp. 1-259–1-266.
26. 26)
  - 5. Black, J., Ellis, T., Makris, D.: ‘Wide area surveillance with a multi camera network’. IEE Intelligent Distributed Surveillance Systems, London, 2004, pp. 21–25.
27. 27)
  - W. Hu , T. Tan , L. Wang , S. Maybank . A survey on visual surveillance of object motion and behaviors. IEEE Trans. Syst. Man Cybern. C , 3 , 334 - 352
28. 28)
  - W. Hu , M. Hu , X. Zhou , T. Tan . Principal axis-based correspondence between multiple cameras for people tracking. IEEE Trans. Pattern Anal. Mach. Intell. , 4 , 663 - 671
29. 29)
  - 7. Black, J., Ellis, T.: ‘Multi camera image tracking’, Image Vis. Comput., 2006, 24, (11), pp. 1256–1267 (doi: 10.1016/j.imavis.2005.06.002).
30. 30)
  - 11. Dubrofsky, E., Woodham, R.J.: ‘Combining line and point correspondences for homography estimation’. Advances in Visual Computing, Berlin Heidelberg, 2008, pp. 202–213.

Calibration and object correspondence in camera networks with widely separated overlapping views

References

Related content