Tunable kernels for tracking

Details Tunable kernels for tracking Tunable kernels for tracking

2007-01-08

2010-12-14

Chang, Jon (Department: 2624)

Image analysis

Applications

Target tracking or detecting

C348S169000

Reexamination Certificate

active

07853042

ABSTRACT:
A tunable representation for tracking that simultaneously encodes appearance and geometry in a manner that enables the use of mean-shift iterations for tracking is provided. The solution to the tracking problem is articulated into a method that encodes the spatial configuration of features along with their density and yet retains robustness to spatial deformations and feature density variations. The method of encoding of spatial configuration is provided using a set of kernels whose parameters can be optimized for a given class of objects off-line. The method enables the use of mean-shift iterations and runs in real-time. Better tracking results by the novel tracking method as compared to the original mean-shift tracker are demonstrated.

REFERENCES:
patent: 7397948 (2008-07-01), Cohen et al.
patent: 7418113 (2008-08-01), Porikli et al.
patent: 2003/0068082 (2003-04-01), Comaniciu et al.
Veeraraghavan et al. “Combining Multiple Tracking Modalities for Vehicle Tracking at Traffic Intersections.” Proceedings of the 2004 IEEE International Conference on Robotics and Automation, Apr. 2004, pp. 2303-2308.
Porikli et al. “Multi-kernel Object Tracking.” 2005 IEEE International Conference on Multimedia and Expo, Jul. 6, 2005, pp. 1234-1237.
Hager et al. “Multiple Kernel Tracking with SSD.” Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun. 27, 2004, vol. 1, pp. I-790-1-797.
Babu et al. “Robust Tracking with Motion Estimation and Kernel-based Color Modelling.” 2005 IEEE International Conference on Image Processing, Sep. 11, 2005, vol. 1, pp. 717-720.
Park et al. “Object Tracking in MPEG Compressed Video Using Mean-Shift Algorithm.” Proceedings of the 2003 Joint Conference of the Fourth International Conference on Information, Communications and Signal Processing, Dec. 15, 2003, vol. 2, pp. 748-752.
Mittal et al. “Motion-based Background Subtraction Using Adaptive Kernel Density Estimation.” Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun. 27, 2004, vol. 2, pp. II-302-II-309.
S. Birchfield and S. Rangarajan, “Spatiograms versus histograms for region-based tracking,”Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2005.
R. Collins, “Mean-shift blob tracking through scale space”, inProc. IEEE Conf. on Computer Vision and Pattern Recognition, 2003.
D. Comaniciu, “An algorithm for data-driven bandwidth selection,” inIEEE Trans. on Pattern Analysis and Machine Intelligence, 25(2):281-288, Feb. 2003.
D. Comaniciu and P. Meer, “Mean shift: A robust approach toward feature space analysis,” inIEEE Trans. on Pattern Analysis and Machine Intelligence, 24(5):603-619, May 2002.
D. Comaniciu, V. Ramesh, and P. Meer, “Kernel-based object tracking.IEEE Trans. on Pattern Analysis and Machine Intelligence,” in 25(5):564-577, May 2003.
A. Elgammal, R. Duraiswami, and L. S. Davis “Probabilistic tracking in joint feature-spatial spaces,” inProc. IEEE Conf. on Computer Vision and Pattern Recognition, 2003.
A. Jepson, D. Fleet, and T. El-Maraghi, “Robust online appearance models for visual tracking,” inProc. IEEE Conf. on Computer Vision and Pattern Recognition, 2001.
A. Rao, R. Srihari, and Z. Zhang, “Spatial color histograms for content-based image retrieval,” inProc. IEEE Intl. Conf. on Tools with Artificial Intelligence, 1999.
K. She, G. Bebis, H. Gu, and R. Miller, “Vehicle tracking using on-line fusion of color and shape features,” inProc. IEEE Conf. on Intelligent Transportation Systems, 2004.
J. Wang, B. Thiesson, Y. Xu, and M. Cohen, “Image and video segmentation by anisotropic kernel mean shift” inProc. European Conference on Computer Vision, 2004.
Q. Zhao and H. Tao, “Object tracking using color correlogram,” inProc. IEEE Conf. on Computer Vision and Pattern Recognition, 2005.
Z. Zivkovic and B. Krose, “An em-like algorithm for color- histogram-based object tracking,” inProc. IEEE Conf. on Computer Vision and Pattern Recognition, 2004.

Affiliated with

Also associated with

Rating

Tunable kernels for tracking does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Tunable kernels for tracking, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Tunable kernels for tracking will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4231405