3D Object Tracking Using Mean-Shift and Similarity-Based Aspect-Graph Modeling

The mean shift algorithm is a popular method in the field of 2D object tracking due to its simplicity and robustness over slight variations of lighting condition, scale and view-point over time. However, the appearance of 3D object might have distinctive variations for different viewpoints over time. In this work, a novel method for tracking 3D objects using mean-shift algorithm and a 3D object database is proposed to achieve a more precise tracking. A 3D object database using similarity-based aspect-graph is built from 2D images sampled at random intervals from the viewing sphere. Contour and color features of each 2D image are used for modeling the 3D object database. To conduct tracking, a suitable object model is selected from the database and the mean-shift tracking is applied to find the local minima of a similarity measure between the color histograms of the object model and the target image. The effectiveness of the proposed method is demonstrated by experiments with objects rotating and translating in space.

[1]  Isaac Weiss,et al.  Model-Based Recognition of 3D Objects from Single Images , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Stanley T. Birchfield,et al.  Spatiograms versus histograms for region-based tracking , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  J. Canny.  A Computational Approach toEdgeDetection , 1986 .

[4]  Zhiyong Huang,et al.  Kernel-based method for tracking objects with rotation and translation , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[5]  Visvanathan Ramesh,et al.  Tunable Kernels for Tracking , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[6]  G. Peters.  Theories of Three-Dimensional Object Perception A Survey , 2000 .

[7]  J. Koenderink,et al.  The singularities of the visual mapping , 1976, Biological Cybernetics.

[8]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Jwu-Sheng Hu,et al.  Robust Background Subtraction with Shadow and Highlight Removal for Indoor Surveillance , 2006, IROS.

[10]  Jerry L. Prince,et al.  Gradient vector flow: a new external force for snakes , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Jwu-Sheng Hu,et al.  Shape Memorization and Recognition of 3D Objects Using a Similarity-Based Aspect-Graph Approach , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[12]  Benjamin B. Kimia,et al.  A Similarity-Based Aspect-Graph Approach to 3D Object Recognition , 2004, International Journal of Computer Vision.

[13]  Kai She,et al.  Vehicle tracking using on-line fusion of color and shape features , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

[14]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Robert T. Collins,et al.  Mean-shift blob tracking through scale space , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..