Abstract
Among the multitude of probabilistic tracking techniques, the Continuously Adaptive Mean Shift (CAMSHIFT) algorithm has been one of the most popular. Though several modifications have been proposed to the original formulation of CAMSHIFT, limitations still exist. In particular the algorithm underperforms when tracking textured and patterned objects. In this paper we generalize CAMSHIFT for the purposes of tracking such objects in non-stationary backgrounds. Our extension introduces a novel object modeling technique, while retaining a probabilistic back projection stage similar to the original CAMSHIFT algorithm, but with considerably more discriminative power. The object modeling now evolves beyond a single probability distribution to a more generalized joint density function on localized color patterns. In our framework, multiple co-occurrence density functions are estimated using information from several color channel combinations and these distributions are combined using an intuitive Bayesian approach. We validate our approach on several aerial tracking scenarios and demonstrate its improved performance over the original CAMSHIFT algorithm and one of its most successful variants.
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
Arvis, V., et al.: Generalization of the cooccurrence matrix for colour images: application to colour texture classification. Image Analysis & Stereology 23, 63–72 (2004)
Bradski, G.R.: Computer vision face tracking for use in a perceptual user interface. Intel Technology Journal (1998)
Cheng, Y.: Mean shift, mode seeking, and clustering. PAMI 17, 790–799 (1995)
Collins, R., Zhou, X., Teh, S.K.: An open source tracking testbed and evaluation web site. In: IEEE Intl. Workshop on Performance Evaluation of Tracking and Surveillance (2005)
Comaniciu, D., Meer, P.: Robust analysis of feature spaces: color image segmentation. In: CVPR, pp. 750–755 (1997)
Exner, D., Bruns, E., Kurz, D., Grundhofer, A., Bimber, O.: Fast and robust CAMShift tracking. In: CVPR Workshop, pp. 9–16 (2010)
Fukunaga, K.: Introduction to Statistical Pattern Recognition. Academic Press, Boston (1990)
Allen, J.G., et. al.: Object tracking using CAMSHIFT algorithm and multiple quantized feature spaces. In: Proc. of the Pan-Sydney Area Wkshp on Visual Information Proc., pp. 3–7 (2004)
Tian, G., Hu, R., Wang, Z., Fu, Y.: Improved object tracking algorithm based on new HSV color probability model. In: Yu, W., He, H., Zhang, N. (eds.) ISNN 2009, Part II. LNCS, vol. 5552, pp. 1145–1151. Springer, Heidelberg (2009)
Ghazali, K., Ma, J., Xiao, R.: Driver’s face tracking based on improved CAMSHIFT. Intl. J. of Image Graphics and Signals Processing 5, 1–7 (2013)
Haber, R., Peter, A., et al. C.E.O.: A support vector machine for terrain classification in on-demand deployments of wireless sensor networks. In: IEEE Systems Conference (2013)
Haralick, R., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Transactions on Systems Man and Cybernetics 3, 610–621 (1973)
Hidayatullah, P., Konik, H.: CAMSHIFT improvement on multi-hue object and multi-object tracking. In: 3rd European Workshop on Visual Information Processing, pp. 143–148 (2011)
Liu, X., Chu, H., Li, P.: Research of the improved CAMSHIFT tracking algorithm. In: Intl. Conf. on Mechanical and Automation Engineering, pp. 968–972 (2007)
Ning, J., Zhang, L., Zhang, D., Wu, C.: Robust object tracking using joint color-texture histogram. Intl. J. of PRIA 23, 1245–1263 (2009)
Nouar, O., Ali, G., Raphael, C.: Improved object tracking with CAMSHIFT algorithm. In: IEEE Intl. Conf. on Acoustics Speech and Signal Processing, pp. 11–14 (2006)
See, A., Bin, K., Kang, L.Y.: Face detection and tracking utilizing enhanced CAMSHIFT model. Intl. J. of Innovative Computing Innovation and Control 3, 597–608 (2007)
Stolkin, R., et. al.: Efficient visual servoing with the ABCshift tracking algorithm. In: IEEE Intl. Conf. on Robotics and Automation, pp. 3219–3224 (2008)
Xia, J., Wu, J., Zhai, H., Cuitis, Z.: Moving vehicle tracking based on double difference and CAMSHIFT. In: Proc. of the Intl. Symposium on Information Processing (2009)
Yue, Y., Gao, Y., Zhang, X.: An improved CAMSHIFT based on dynamic background. In: 1st Intl. Conf. on Information Science and Engineering, pp. 1141–1144 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Moyou, M. et al. (2015). Bayesian Fusion of Back Projected Probabilities (BFBP): Co-occurrence Descriptors for Tracking in Complex Environments. In: Battiato, S., Blanc-Talon, J., Gallo, G., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2015. Lecture Notes in Computer Science(), vol 9386. Springer, Cham. https://doi.org/10.1007/978-3-319-25903-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-25903-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25902-4
Online ISBN: 978-3-319-25903-1
eBook Packages: Computer ScienceComputer Science (R0)