Complex motion measurement using genetic algorithm

Jianjun Shen; Dan Tu; Zhenkang Shen

doi:10.1117/12.294526

12 December 1997 Complex motion measurement using genetic algorithm

Jianjun Shen, Dan Tu, Zhenkang Shen

Proceedings Volume 3173, Ultrahigh- and High-Speed Photography and Image-based Motion Measurement; (1997) https://doi.org/10.1117/12.294526
Event: Optical Science, Engineering and Instrumentation '97, 1997, San Diego, CA, United States

Abstract

Genetic algorithm (GA) is an optimization technique that provides an untraditional approach to deal with many nonlinear, complicated problems. The notion of motion measurement using genetic algorithm arises from the fact that the motion measurement is virtually an optimization process based on some criterions. In the paper, we propose a complex motion measurement method using genetic algorithm based on block-matching criterion. The following three problems are mainly discussed and solved in the paper: (1) apply an adaptive method to modify the control parameters of GA that are critical to itself, and offer an elitism strategy at the same time (2) derive an evaluate function of motion measurement for GA based on block-matching technique (3) employ hill-climbing (HC) method hybridly to assist GA's search for the global optimal solution. Some other related problems are also discussed. At the end of paper, experiments result is listed. We employ six motion parameters for measurement in our experiments. Experiments result shows that the performance of our GA is good. The GA can find the object motion accurately and rapidly.

Citation Download Citation

Jianjun Shen, Dan Tu, and Zhenkang Shen "Complex motion measurement using genetic algorithm", Proc. SPIE 3173, Ultrahigh- and High-Speed Photography and Image-based Motion Measurement, (12 December 1997); https://doi.org/10.1117/12.294526

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available