Abstract
We propose a parallel Mean Shift (MS) tracking algorithm on Graphics Processing Unit (GPU) using Compute Unified Device Architecture (CUDA). Traditional MS algorithm uses a large number of color histogram, say typically 16x16x16, which makes parallel implementation infeasible. We thus employ K-Means clustering to partition the object color space that enables us to represent color distribution with a quite small number of bins. Based on this compact histogram, all key components of the MS algorithm are mapped onto the GPU. The resultant parallel algorithm consist of six kernel functions, which involves primarily the parallel computation of the candidate histogram and calculation of the Mean Shift vector. Experiments on public available CAVIAR videos show that the proposed parallel tracking algorithm achieves large speedup and has comparable tracking performance, compared with the traditional serial MS tracking algorithm.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Comaniciu, D., Ramesh, V., Meer, P.: Real-time Tracking of Non-rigid Objects Using Mean Shift. In: Proc. IEEE Conf. Comp. Vis. Patt. Recog., pp. 142–149. Hilton Head Island, South Carolina (2000)
Collins, R.T.: Mean-shift Blob Tracking Through Scale Space. In: Proc. IEEE Conf. Comp. Vis. Patt. Recog., Madison, Wisconsin, pp. 234–241 (2003)
Birchfield, S.T., Rangarajan, S.: Spatiograms versus Histograms for Region-based Tracking. In: Proc. IEEE Conf. Comp. Vis. Patt. Recog., San Diego, CA, USA, pp. 1158–1163 (2005)
Zhao, Q., Tao, H.: Object Tracking using Color Correlogram. In: IEEE Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS) in conjunction with ICCV, pp. 263–270 (2005)
Yilmaz, A.: Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection. In: Proc. IEEE Conf. Comp. Vis. Patt. Recog., Minneapolis, Minnesota, pp. 1–6 (2007)
Zhang, H., Huang, W., Huang, Z., Li, L.: Affine object tracking with kernel-based spatial-color representation. In: Proc. IEEE Conf. Comp. Vis. Patt. Recog., San Diego, CA, USA, pp. 293–300 (2005)
Leichter, I., Lindenbaum, M., Rivlin, E.: Visual Tracking by Affine Kernel Fitting Using Color and Object Boundary. In: Proc. Int. Conf. Comp. Vis., Rio de, Janeiro, Brazil, pp. 1–6 (2007)
NVIDIA CUDA Homepage, http://developer.nvidia.com/object/cuda.html
Li, P.: A clustering-based color model and integral images for fast object tracking. Signal Processing: Image Communication, 676–687 (2006)
EC funded CAVIAR project/IST 2001 37540 (2004), http://homepages.inf.ed.ac.uk/rbf/CAVIAR/
Bajramovic, F., Grabl, C., Denzler, J.: Efficient Combination of Histograms for Real-Time Tracking Using Mean-Shift and Trust-Region Optimization. In: Proc. 27th DAGM Symposium on Pattern Recognition, Vienna, Austria, pp. 254–261 (2005)
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
Li, P., Xiao, L. (2009). Mean Shift Parallel Tracking on GPU. In: Araujo, H., Mendonça, A.M., Pinho, A.J., Torres, M.I. (eds) Pattern Recognition and Image Analysis. IbPRIA 2009. Lecture Notes in Computer Science, vol 5524. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02172-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-02172-5_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02171-8
Online ISBN: 978-3-642-02172-5
eBook Packages: Computer ScienceComputer Science (R0)