Abstract
This paper presents a robust implementation of an object tracker able to tolerate partial occlusions, rotation and scale for a variety of different objects. The objects are represented by collections of interest points which are described in a multi-resolution framework, giving a representation of those points at different scales. Inspired by [1], a stack of descriptors is built only the first time that the interest points are detected and extracted from the region of interest. This provides efficiency of representation and results in faster tracking due to the fact that it can be done off-line. An Unscented Kalman Filter (UKF) using a constant velocity model estimates the position and the scale of the object, with the uncertainty in the position and the scale obtained by the UKF, the search of the object can be constrained only in a specific region in both the image and in scale.
The use of this approach shows an improvement in real-time tracking and in the ability to recover from full occlusions.
Chapter PDF
References
Chekhlov, D., Pupilli, M., Mayol-Cuevas, W., Calway, A.: Real-time and robust monocular slam using predictive multi-resolution descriptors. In: 2nd International Symposium on Visual Computing (November 2006)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Computer Vision 2(60), 91–110 (2004)
Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. IJCV 1(60), 63–86 (2004)
Harris, C.J., Stephens, M.: A combined corner and edge detector. In: Proc. 4th Alvey Vision Conferences, pp. 147–151 (1988)
Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. International Journal of Computer Vision 2(37), 151–172 (2000)
Bay, H., Tuytelaars, T., Van Gool, L.: SURF: Speeded up robust features. In: Proceedings of the ninth European Conference on Computer Vision (May 2006)
Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Transactions on Pattern Annalysis and Machine Intelligence 25, 564–577 (2003)
Rasmussen, C., Toyama, K., Hager, G.D.: Traking objects by color alone. Technical report, Yale University (June 1996)
Perez, P., Hue, C., Vermaak, J., Gagnet, M.: Color-based probabilistic tracking. In: ECCV, pp. 661–675 (2002)
Pahlavan, K., Eklundh, J.O.: A head-eye system- analysis and design. CVGIP: Image Understanding 56, 41–56 (1992)
Tissainayagam, P., Suter, D.: Object tracking in image sequences using point features. Pattern Recognition 38, 105–113 (2005)
Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: CVPR, pp. 142–149 (2000)
Serby, D., Meier, E.K., Gool, L.V.: Probabilistic object tracking using multiple features. In: ICPR 2004, pp. 184–187 (2004)
Cipolla, R., Yamamoto, M.: Stereoscopic tracking of bodies in motion. Image and Vision Computing 8(1), 85–90 (1990)
Blake, A., Curwen, R., Zisserman, A.: A framework for spatiotemporal control in the tracking of visual contours. Int. J. Computer Vision 11(2), 127–145 (1993)
Blake, A., Isard, M.: Active Contours. Springer, London (1998)
Julier, J., Uhlmann, K.: Unscented filtering and nonlinear estimation. Proceedings of the IEEE 93, 401–422 (2004)
Julier, S.J., Uhlmann, J.K.: A new extension of the kalman filter to nonlinear systems. In: AeroSense: The 11th Int. Symp. on Aerospace/Defence Sensing, Simulation and Controls (1997)
Doucet, A., Godsill, S., Andrieu, C.: On sequential monte carlo sampling methods for bayesian filtering. Statistics and Computing 10(3), 197–208 (2000)
Perez, P., Vermaak, J., Blake, A.: Data fusion for visual tracking with particles. Proceedings of the IEEE 92, 495–513 (2004)
Liu, J., Chen, R.: Sequential monte carlo methods for dynamic systems. American Statistical Association 93, 1032–1044 (1998)
Viola, P., Jones, M.: Rapid object detection using boosted cascade of simple features. Computer Vision and Pattern Recognition 1, 511–518 (2001)
Heckbert Paul, S.: Fundamentals of texture mapping and image warping. Master’s thesis, University of California, Berkeley. Dept. of Electrical Engineering and Computer Science (June 1989)
Video of the object I. http://www.youtube.com/watch?v=bpfkVq-w53E
Video of the object II. http://www.youtube.com/watch?v=eR0IMpRKOc8
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Carrera, G., Savage, J., Mayol-Cuevas, W. (2007). Robust Feature Descriptors for Efficient Vision-Based Tracking. In: Rueda, L., Mery, D., Kittler, J. (eds) Progress in Pattern Recognition, Image Analysis and Applications. CIARP 2007. Lecture Notes in Computer Science, vol 4756. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76725-1_27
Download citation
DOI: https://doi.org/10.1007/978-3-540-76725-1_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76724-4
Online ISBN: 978-3-540-76725-1
eBook Packages: Computer ScienceComputer Science (R0)