Robust Object Tracking Based on Modified Mean-Shift Algorithm

Wei Li; Xing Wei Li; Rui Tao Lu; Dong Dong Zou

doi:10.4028/www.scientific.net/AMM.543-547.2738

Paper Titles

Based on Semi-Supervised Clustering with the Boost Similarity Metric Method for Face Retrieval
p.2720

Moving Shadow Detection Method Using Logistic Regression
p.2724

On-Line Decrypting: A Homomorphic Realization for Network Coding
p.2728

A Preamble Detecting Algorithm of MOD-5 Interrogating Signal
p.2733

Robust Object Tracking Based on Modified Mean-Shift Algorithm
p.2738

Preparation and Measurement of Quantum State between Two-Dimensional Dots in Quantum Network
p.2742

The Research of Face Verification Based on Perceptron Algorithm
p.2746

Study on Improvement of MUSIC Estimation Method
p.2750

Modeling of Ground Based Space Surveillance System Based on MAS Method
p.2755

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 543-547Robust Object Tracking Based on Modified...

Robust Object Tracking Based on Modified Mean-Shift Algorithm

Abstract:

In this article, aiming at the flaws in traditional Mean-shift algorithm for object tracking, we improve the traditional algorithm based on the fusion of Grayscale and Gradient using a layered approach. This algorithm can describe the object more exactly by using Grayscale and Gradient dual tracking factors in object tracking; And it makes up the flaws in traditional Mean-shift algorithm for information expression of spatial location by using layered approach and spatial histogram in describing object. Experimental results show that modified Mean-shift algorithm is superior to traditional Mean-shift algorithm in object tracking with better Robustness and precision, and it can suit deformation, spin, interference, shield and more complex tracking problems.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 543-547)

Pages:

2738-2741

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.543-547.2738

Citation:

Cite this paper

Online since:

March 2014

Authors:

Wei Li*, Xing Wei Li, Rui Tao Lu, Dong Dong Zou

Keywords:

Fusion of Grayscale and Gradient, Layered Approach, Modified Mean-Shift Algorithm, Object Tracking

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] TIAN Xiao-dong, etc. A Fast Object Tracking Algorithm Based on Sonar Image Sequences[J]. Computer simulation, 2007, 24(7): 5-8. (In Chinese).

Google Scholar

[2] ZHOU Chang, etc. object tracking method based on local image descriptor [J]. Journal of Zhejiang University, 2008, 42(7): 1179-1183. (In Chinese).

Google Scholar

[3] HU Jian-wang, etc. A Particle Filter for Tracking Moving Targets in Sequence Image [J]. Fire Control & Command Control, 2012, 37(2): 76-79. (In Chinese).

Google Scholar

[5] BI Hua-jun, etc. Target Tracking Based on Image Sequence Using Particle Filter [J]. Computer simulation, 2006, 23(1): 184-186. (In Chinese).

Google Scholar

[6] SHI Hua, LI Cui-hua. A New Algorithm of Moving Object Tracking in Video Sequences [J]. Computer Engineering and Application, 2005, 10: 56-58. (In Chinese).

Google Scholar

[7] SHI Ze-lin, etc. Research on Image Matching and Target Tracking Through Singular Value Decomposition [J]. MINI— MICR0 SYSTEM S, 2005, 26(9): 1643-1646. (In Chinese).

Google Scholar

[8] GE Xin, LIU Yuan. Adaptive image matching target tracking algorithm based on position estimation[J]. Computer Engineering and Design, 2009, 30(24): 5673-5680. (In Chinese).

Google Scholar