Abstract
This report contributes a new approach for the robust tracking of humans’ heads and faces based on a spatio-temporal scene analysis. The framework comprises aspects of structure and motion problems, as there are feature extraction, spatial and temporal matching, re-calibration, tracking, and reconstruction. The scene is acquired through a calibrated stereo sensor. A cue processor extracts invariant features in both views, which are spatially matched by geometric relations. The temporal matching takes place via prediction from the tracking module and a sixmilarity transformation of the features’ 2D locations between both views. The head is reconstructed and tracked in 3D. The re-projection of the predicted structure limits the search space of both the cue processor as well as the re-construction procedure. Due to the focused application, the instability of calibration of the stereo sensor is limited to the relative extrinsic parameters that are re-calibrated during the re-construction process. The framework is practically applied and proven. First experimental results will be discussed and further steps of development within the project are presented.
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
Im, S.-B., Hwang, K.-S., Cho, S.-B.: A Bayesian network framework for vision based semantic scene understanding. In: 16th IEEE Int. Conf. on Robot & Human Interactive Communication, Jeju, Korea, August 26-29, pp. 839–844 (2007)
Cusano, C., Ciocca, G., Schettini, R., Brambilla, C.: Semantic Labeling of Digital Photos by Classification. In: Proc. of Internet Imaging IV, vol. SPIE 5018, pp. 296–303 (2003)
Makris, D., Ellis, T.J.: Learning Semantic Scene Models from Observing Activity in Visual Surveillance. IEEE Transactions on Systems Man and Cybernetics - Part B 35(3), 397–408 (2005)
Steffens, M., Krybus, W., Kohring, C.: Ein Ansatz zur visuellen Fahrerbeobachtung, Sensorik und Algorithmik zur Beobachtung von Autofahrern unter realen Bedingungen. In: VDI-Konferenz BV 2007, Regensburg, Deutschland (2007)
Lay, G., Zelinsky, A.: A fast radial symmetry transform for detecting points of interest. Technical report, Australien National University, Canberra (2003)
Pilu, M.: Uncalibrated stereo correspondence by singular valued decomposition. Technical report, HP Laboratories Bristol (1997)
Scott, G., Longuet-Higgins, H.: An algorithm for associating the features of two patterns. In: Proceedings of the Royal Statistical Society of London, vol. B244, pp. 21–26 (1991)
Welch, G., Bishop, G.: An introduction to the kalman filter (July 2006)
Steffens, M.: Polar Rectification and Correspondence Analysis. Technical Report Laboratory for Image Processing Soest, South Westphalia University of Applied Sciences, Germany (2008)
Cheever, E.: Kalman filter (2008)
Torr, P.H.S.: A structure and motion toolkit in matlab. Technical report, Microsoft Research (2002)
Oberle, W.F.: Stereo camera re-calibration and the impact of pixel location uncertainty. Technical Report ARL-TR-2979, U.S. Army Research Laboratory (2003)
Pollefeys, M.: Visual 3D modeling from images. Technical report, University of North Carolina - Chapel Hill, USA (2002)
Newman, R., Matsumoto, Y., Rougeaux, S., Zelinsky, A.: Real-Time Stereo Tracking for Head Pose and Gaze Estimation. In: FG 2000, pp. 122–128 (2000)
Heinzmann, J., Zelinsky, A.: 3-D Facial Pose and Gaze Point Estimation using a Robust Real-Time Tracking Paradigm, Canberra, Australia (1997)
Seeing Machines: WIPO Patent WO/2004/003849
Loy, G., Fletcher, L., Apostoloff, N., Zelinsky, A.: An Adaptive Fusion Architecture for Target Tracking, Canberra, Australia (2002)
Kähler, O., Denzler, J., Triesch, J.: Hierarchical Sensor Data Fusion by Probabilistic Cue Integration for Robust 3-D Object Tracking. Passau, Deutschland (2004)
Mills, S., Novins, K.: Motion Segmentation in Long Image Sequences, Dunedin, New Zealand (2000)
Mills, S., Novins, K.: Graph-Based Object Hypothesis, Dunedin, New Zealand (1998)
Mills, S.: Stereo-Motion Analysis of Image Sequences, Dunedin, New Zealand (1997)
Kropatsch, W.: Tracking with Structure in Computer Vision TWIST-CV. Project Proposal, Pattern Recognition and Image Processing Group, TU Vienna (2005)
Steffens, M.: Close-Range Photogrammetry. Technical Report Laboratory for Image Processing Soest, South Westphalia University of Applied Sciences, Germany (2008)
Kieneke, S., Steffens, M., Krybus, W.: Analysis and Implementation of Methods for Face Tracking. Technical Report Laboratory for Image Processing Soest, South Westphalia University of Applied Sciences, Germany (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Steffens, M., Krybus, W., Kohring, C., Morton, D. (2009). Spatio-Temporal Tracking of Faces by Stereo Vision. In: Gagalowicz, A., Philips, W. (eds) Computer Vision/Computer Graphics CollaborationTechniques. MIRAGE 2009. Lecture Notes in Computer Science, vol 5496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01811-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-01811-4_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01810-7
Online ISBN: 978-3-642-01811-4
eBook Packages: Computer ScienceComputer Science (R0)