Algorithm Optimization of Motion Tracking Based on Optical Flow

Dong Ming Liu; Chao Liu; Hai Wei Mu

doi:10.4028/www.scientific.net/AMR.926-930.2938

Paper Titles

A Topology Aggregation Scheme in Multi-Domain WDM-TDM Networks
p.2919

A Way to Predict and Evaluate of Software Maintainability Based on Machine Learning
p.2924

Accelerate Bregman MRI Image Reconstruction Algorithm
p.2928

Algorithm Based on the Vertex Similarity of the Network for Detecting Community Structure
p.2932

Algorithm Optimization of Motion Tracking Based on Optical Flow
p.2938

An Algorithm Based on Self-Organizing Kohonen’s SOM for Color Image Segmentation
p.2942

An Application Research on Adaptive Learning Algorithm in Image Recognition
p.2947

An Efficient Packet Scheduling and Resource Allocation Algorithm for Practical Multi-Layer Systems
p.2951

An Improved Algorithm of Weighted Centroid Algorithm Based on RSSI
p.2955

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 926-930Algorithm Optimization of Motion Tracking Based on...

Algorithm Optimization of Motion Tracking Based on Optical Flow

Abstract:

Optical flow is an important kind of video motion tracking algorithm, and Lucas-Kanade (LK) algorithm is an effective differential method in terms of calculating optical flow. The 3D Gaussian smoothing filter is properly introduced in the image preprocessing stage of the LK algorithm, which makes it possible to increase the correlation of the adjacent pixels in the time axis, improve the blur effect of the video image and overcome the 2D Gaussian filters disadvantage that is not suitable for the video image processing. More importantly, the optimized 3D non-Gaussian matching filter is chosen during the 3D derivative calculating, and it is capable of reducing the error rate of the velocity vector calculation and enhancing the calculation accuracy of the optical flow.

You might also be interested in these eBooks

Progress in Applied Sciences, Engineering and Technology

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 926-930)

Pages:

2938-2941

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.926-930.2938

Citation:

Cite this paper

Online since:

May 2014

Authors:

Dong Ming Liu, Chao Liu*, Hai Wei Mu

Keywords:

3D Non-Gaussian Derivative Filter, LK Algorithm, Motion Tracking, Optical Flow

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] B.K.P. Horn, B.G. Schunck, Artificial Intelligence. 17 (1981)185-204.

Google Scholar

[2] Bruce D. Lucas, Takeo Kanade. T, An iterative image registration technique with an application to stereo vision. Proceedings of the 1981 DARPA Image Understanding Workshop, April, 1981, pp.121-130.

Google Scholar

[3] Ajit Singh, An estimation-theoretic framework for image-flow computation, Proceeding IEEE ICCV, Osaka, Japan, 1990, pp.168-177.

Google Scholar

[4] D.J. Heeger, International Journal of Computer Vision. 1 (1988) 279-302.

Google Scholar

[5] J.L. Barron, D.J. Fleet, International Journal of Computer Vision. 12 (1994) 43-45.

Google Scholar

[6] J.L. Barron, Computer Vision and Pattern Recognition. 10 (1992) 236-242.

Google Scholar

[7] D. Javier, R. Eduardo, Computer Vision and Image Understanding. 112 (2008) 262-273.

Google Scholar

[8] E.P. Simoncelli, Design of multi-dimensional derivative filters, IEEE International Conference on Image Processing, 1 (1994) 791-793.

Google Scholar