Abstract
A novel image-registration method is presented which is applicable to multi-camera systems viewing human subjects in motion. The method is suitable for use with indoor or outdoor surveillance scenes. The paper summarizes an efficient walk-detection and biometric method for extraction of image characteristics which enables the walk properties of the viewed subjects to be used to establish corresponding image-points for the purpose of image-registration between cameras. The leading leg of the walking subject is a good feature to match, and the presented method can identify this from two successive walk-steps (one walk cycle). Using this approach, the described method can detect a sufficient number of corresponding points for the estimation of correspondence between views from two cameras. An evaluation study has demonstrated the method’s feasibility in the context of an actual indoor real-time surveillance system.
This work was supported by the NoE MUSCLE project of the EU.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barnard, S.T., Thompson, W.B.: Disparity analysis of images. IEEE Trans. PAMI 2(4), 333–340 (1980)
Cheng, J.K., Huang, T.S.: Image registration by matching relational structures. Pattern Recog. 17(1), 149–159 (1984)
Weng, J., Ahuja, N., Huang, T.S.: Matching two perspective views. IEEE Trans. PAMI 14(8), 806–825 (1992)
Zhang, Z., Deriche, R., Faugeras, O., Luong, Q.-T.: A robust technique for matching two uncalibrated images through the recovery of the unknown Epipolar Geometry. Artificial Intelligence Journal 78, 87–119 (1995)
Lee, L., Romano, R., Stein, G.: Monitoring activities from multiple video streams: establishing a common coordinate frame. IEEE Trans. PAMI 22(8) (2000)
Szlávik, Z., Havasi, L., Szirányi, T.: Estimation of common groundplane based on co-motion statistics. In: Campilho, A.C., Kamel, M.S. (eds.) ICIAR 2004. LNCS, vol. 3212, pp. 347–354. Springer, Heidelberg (2004)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)
Havasi, L., Szlávik, Z.: Symmetry feature extraction and understanding. In: Proc. CNNA 2004, pp. 255–260 (2004)
Stauffer, C., Eric, W., Grimson, L.: Learning patterns of activity using real-time tracking. IEEE Trans. on PAMI 22(8), 747–757 (2000)
Havasi, L., Benedek, C., Szlávik, Z., Szirányi, T.: Extracting structural fragments of overlapping pedestrians. In: IASTED VIIP (2004)
Havasi, L., Szlávik, Z., Szirányi, T.: Pedestrian detection using derived third-order symmetry of legs. In: ICCVG. Kluwer, Dordrecht (2004)
Havasi, L., Szlávik, Z., Sziranyi, T.: Eigenwalks: Walk detection and biometrics from symmetry patterns. In: IEEE ICIP (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Havasi, L., Szlávik, Z., Szirányi, T. (2005). Use of Human Motion Biometrics for Multiple-View Registration. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2005. Lecture Notes in Computer Science, vol 3708. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11558484_5
Download citation
DOI: https://doi.org/10.1007/11558484_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29032-2
Online ISBN: 978-3-540-32046-3
eBook Packages: Computer ScienceComputer Science (R0)