Real-time tracking objects in different scenes on DSP and FPGA platform

Qiang Wang; Zhanhong Gao; Jiangtao Li

doi:10.1117/12.832605

30 October 2009 Real-time tracking objects in different scenes on DSP and FPGA platform

Qiang Wang, Zhanhong Gao, Jiangtao Li

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74954V (2009) https://doi.org/10.1117/12.832605
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

We propose three adaptive tracking approaches in different environments for our particular application. Poid tracking algorithm with iterative image segmentation and robust threshold is adopted for single object tracking in simple background. Multiple targets are detected and tracked using contour tracking algorithm in simple scenarios. Correlation tracking algorithm is more suitable to track an interesting moving object in complex scenes. Moreover, a programmable hardware based on TMS320DM642 DSP and Spatran3E FPGA is put forward. Then the software design methods and implementation on this platform are simultaneously introduced. The different track mode is selected by instructions from control computer. Experiments show that the three tracking algorithms are implemented in real time.

Citation Download Citation

Qiang Wang, Zhanhong Gao, and Jiangtao Li "Real-time tracking objects in different scenes on DSP and FPGA platform", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74954V (30 October 2009); https://doi.org/10.1117/12.832605

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