Abstract
Object tracking is a fundamental challenge in computer vision. For real-time tracking, the efficiency and robustness of the Mean-shift algorithm makes it a popular choice. However, the scale of the Mean-shift kernel is a crucial parameter and no clear mechanism exists presently for updating the scale when a size-changing object is tracked. In this paper, a new method is introduced using projective geometry to determine the size of the object, and in turn the scale of the Mean-shift kernel. In the initial step of the algorithm, the geometric information of the scene is obtained automatically (or manually). With the geometric information, the size of the object is updated. The experimental results show that this algorithm is stable, efficient and outperforms the Mean-shift baseline and other kernel updating methods, such as CAMSHIFT.
Similar content being viewed by others
References
Benfold B, Reid I (2011) Unsupervised learning of a scene-specific coarse gaze estimator. In: ICCV
Bradski GR (1998) Computer vision face tracking for use in a perceptual user interface. In: IEEE workshop on applications of computer vision, Princeton, NJ, pp 214–219
Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698
Cheng Y (1995) Mean shift, mode seeking, and clustering. IEEE Trans Pattern Anal Mach Intell 17(8):790–799
Chu DM, Smeulders AWM (2010) Thirteen hard cases in visual tracking. In: IEEE workshop on performance evaluation of tracking and surveillance
Collins RT (2003) Mean-shift blob tracking through scale space. In: IEEE Computer Society conference on computer vision and pattern recognition, Vancouver, vol II, pp 234–240
Comaniciu D, Ramesh V, Meer P (2000) Real-time tracking of non-rigid objects using mean shift. In: IEEE international conference on computer vision and pattern recognition, South Carolina, pp 142–149
Comaniciu D, Ramesh V, Meer P (2001) The variable bandwidth mean shift and data-driven scale selection. In: International conference on computer vision, vol I, pp 438–445
Comaniciu D, Ramesh V, Meer P (2003) Kernel-based object tracking. IEEE Trans Pattern Anal Mach Intell 25(5):564–577
Everts I, van Gemert JC, Gevers Th (2012) Per-patch descriptor selection using surface and scene properties. In: European conference on computer vision
Hartley R, Zisserman A (2003) Multiple view geometry in computer vision, 2nd edn. Cambridge University Press, Cambridge
Hedau V, Hoiem D, Forsyth D (2009) Recovering the spatial layout of cluttered room. In: Proc. ICCV
Lindeberg T (1998) Feature detection with automatic scale selection. Int J Comput Vis 30(2):79–116
Lou Z, Jiang G, Wu C (2009) Mean-shift tracking of variable kernel based on projective geometry. In: International congress on image and signal processing, Tianjin
Lou Z, Jiang G, Jia L, Wu C (2010) Monocular 3D tracking of mean-shift with scale adaptation based on projective geometry. In: The international conference on multimedia technology, Ningbo
Lucena M, Fuertes JM, Blanca NP, Jimenez MJM (2010) Tracking people in video sequences using multiple models. Multimedia Tools Appl 49(2):371–403
Peng N, Yang J, Liu Z, Zhang F (2005) Automatic selection of kernel-bandwidth for mean-shift object tracking. J Softw 16(9):1542–1550
Qi SM, Huang XW, Yi HF (2007) Object tracking by anisotropic kernel mean shift. J Electron Inf Technol 29(3):686–689
Sicre R, Nicolas H (2011) Improved Gaussian mixture model for the task of object tracking. In: 14th international conference on computer analysis of images and patterns
Sotelo MA, Rodriguez FJ, Magdalena L, Bergasa LM, Boquete L (2004) A color vision-based lane tracking system for autonomous driving on unmarked roads. Auton Robots 16(1):95–116
Tyagi A, Keck M, Davis JW, Potamianos G (2006) Kernel-based 3D tracking. In: IEEE conference on computer vision and pattern recognition
Yilmaz A (2007) Object tracking by asymmetric kernel mean shift with automatic scale and orientation selection. In: IEEE conference on computer vision and pattern recognition. IEEE, Minneapolis, pp 1–6
Zhou H, Yuan Y, Shi CM (2009) Object tracking using SIFT features and mean shift. Comput Vis Image Understand 113:345–352
Zhu S (2006) A study of mean shift and correlative algorithm in visual tracking. PhD thesis, ZheJiang University
Zhu S, Zhu S (2006) Algorithm of target tracking based on mean shift with adaptive bandwidth of kernel function. J Optoelectron Eng 33(8):11–16
Zivkovic Z, Krose B (2004) An EM-like algorithm for color-histogram-based object tracking. In: Proc. IEEE conference on computer vision and pattern recognition, vol 1, pp 798–803
Zivkovic Z, Krose B (2004) A probabilistic model for an EM-like object tracking algorithm using color histograms. In: Proc. 6th IEEE int. workshop on performance evaluation of tracking and surveillance
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lou, Z., Jiang, G. & Wu, C. 2D scale-adaptive tracking based on projective geometry. Multimed Tools Appl 72, 905–924 (2014). https://doi.org/10.1007/s11042-013-1407-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-013-1407-y