30 October 2009 Real-time tracking objects in different scenes on DSP and FPGA platform
Author Affiliations +
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.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Qiang Wang, Qiang Wang, Zhanhong Gao, Zhanhong Gao, Jiangtao Li, 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); doi: 10.1117/12.832605; https://doi.org/10.1117/12.832605
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT


Back to Top