Abstract
This paper presents a novel feature set for visual tracking that is derived from “oriented energies”. More specifically, energy measures are used to capture a target’s multiscale orientation structure across both space and time, yielding a rich description of its spatiotemporal characteristics. To illustrate utility with respect to a particular tracking mechanism, we show how to instantiate oriented energy features efficiently within the mean shift estimator. Empirical evaluations of the resulting algorithm illustrate that it excels in certain important situations, such as tracking in clutter with multiple similarly colored objects and environments with changing illumination. Many trackers fail when presented with these types of challenging video sequences.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. Comp. Surv. 38(4), 1–45 (2006)
Lucas, B., Kanade, T.: An iterative image registration technique with application to stereo vision. In: DARPA IUW, pp. 121–130 (1981)
Anandan, P.: A computational framework and an algorithm for the measurement of visual motion. IJCV 2(3), 283–310 (1989)
Shi, J., Tomasi, C.: Good features to track. CVPR 1, 593–600 (1994)
Sethi, I., Jain, R.: Finding trajectories of feature points in monocular images. PAMI 9(1), 56–73 (1987)
Deriche, R., Faugeras, O.: Tracking line segments. IVC 8(4), 261–270 (1991)
Rangarajan, K., Shah, M.: Establishing motion correspondence. CVGIP 54(1), 56–73 (1991)
Terzopoulos, D., Szeliski, R.: Tracking with kalman snakes. In: Blake, A., Yuille, A. (eds.) Active Vision, pp. 553–556. MIT Press, Cambridge (1992)
Isard, M., Blake, A.: Contour tracking by stochastic propagation of conditional density. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1064, pp. 343–354. Springer, Heidelberg (1996)
Haritaoglu, L., Harwood, D., Davis, L.: W4: Real-time surveillance of people and their activities. PAMI 22(8), 809–830 (2000)
Birchfield, S.: Elliptic head tracking with intensity gradients and color histograms. CVPR 1, 232–237 (1998)
Sigal, L., Sclaroff, S., Athitsos, V.: Estimation and prediction of evolving color distributions for skin segmentation under varying illumination. CVPR 2, 152–159 (2000)
Elgammal, A., Duraiswami, R., Davis, L.: Probabilistic tracking in joint feature-spatial spaces. CVPR 1, 781–788 (2003)
Bolgomolov, Y., Dror, G., Lapchev, S., Rivlin, E., Rudzsky, M.: Classification of moving targets based on motion and appearance. In: BMVC, pp. 142–149 (2003)
Cremers, D., Schnorr, C.: Statistical shape knowledge in variational motion segmentation. IVC 21(1), 77–86 (2003)
Sato, K., Aggarwal, J.: Temporal spatio-velocity transformation and its application to tracking and interaction. CVIU 96(2), 100–128 (2004)
Adelson, E., Bergen, J.: Spatiotemporal energy models for the perception of motion. JOSA 2(2), 284–299 (1985)
Heeger, D.: Optical flow from spatiotemporal filters. IJCV 1(4), 297–302 (1988)
Enzweiler, M., Wildes, R., Herpers, R.: Unified target detection and tracking using motion coherence. Wrkshp. Motion & Video Comp. 2, 66–71 (2005)
Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE PAMI 25(5), 564–575 (2003)
Collins, R.: Mean-shift blob tracking through scale space. CVPR 2, 234–240 (2003)
Zivkovic, Z., Krose, B.: An EM-like algorithm for color-histogram tracking. CVPR 1, 798–803 (2004)
Freeman, W., Adelson, E.: The design and use of steerable filters. IEEE PAMI 13(9), 891–906 (1991)
Brand, M., Kettnaker, V.: Discovery and segmentation of activities in video. IEEE PAMI 22(8), 844–851 (2000)
Derpanis, K., Gryn, J.: Three-dimensional nth derivative of Gaussian separable steerable filters. ICIP 3, 553–556 (2005)
PETS (2006), http://peipa.essex.ac.uk/ipa/pix/pets/
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cannons, K., Wildes, R. (2007). Spatiotemporal Oriented Energy Features for Visual Tracking. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4843. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76386-4_50
Download citation
DOI: https://doi.org/10.1007/978-3-540-76386-4_50
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76385-7
Online ISBN: 978-3-540-76386-4
eBook Packages: Computer ScienceComputer Science (R0)