DocumentCode
3232708
Title
The research on target recognition and image tracking system based on high-speed DSP
Author
Chunfang, Yin ; Dean, Zhao
Author_Institution
Coll. of Electron. & Inf. Eng., Jiangsu Univ., Zhenjiang, China
fYear
2009
fDate
25-28 July 2009
Firstpage
697
Lastpage
700
Abstract
After image tracking having been applied in many fields, people are now paying more and more attention to the research in finding a real-time image tracking system with preferable precision. This system is designed to be a master-slave structure based on PC and TMS320C6201(DSP). With the DSP focusing on image processing a real-time tracking system can be realized. The classical pattern arithmetic ATR is applied in the tracking. In the paper an effective hybrid genetic algorithm (GASA) is adopted in image segmentation. The effect of image segmentation is achieved by combining the capacity of GA to reach the global optimum with the capability of SA to gain the local search ability. A correlation tracking mode optimized by SSDA can improve the tracking probability.
Keywords
arithmetic; correlation methods; digital signal processing chips; genetic algorithms; image recognition; image segmentation; object recognition; probability; real-time systems; search problems; simulated annealing; target tracking; GASA; PC; SSDA; TMS320C6201; correlation tracking mode; global optimum; high-speed DSP; hybrid genetic algorithm; image processing; image segmentation; local search ability; master-slave structure; pattern arithmetic; probability; real-time image tracking system; simulated annealing; target recognition; Computer science; Computer science education; Digital signal processing; Genetic algorithms; Image recognition; Image segmentation; Nonlinear filters; Real time systems; Target recognition; Target tracking; ATR; GASA; SSDA; TMS320C6201; image tracking;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Science & Education, 2009. ICCSE '09. 4th International Conference on
Conference_Location
Nanning
Print_ISBN
978-1-4244-3520-3
Electronic_ISBN
978-1-4244-3521-0
Type
conf
DOI
10.1109/ICCSE.2009.5228336
Filename
5228336
Link To Document