A stream system-on-chip architecture for high speed target recognition based on biologic vision

  • Authors:
  • Nan Wu;Qianming Yang;Mei Wen;Yi He;Changqing Xun;Chunyuan Zhang

  • Affiliations:
  • National Laboratory for Parallel & Distributed Processing Chang Sha, Hu Nan, P. R. of China;National Laboratory for Parallel & Distributed Processing Chang Sha, Hu Nan, P. R. of China;National Laboratory for Parallel & Distributed Processing Chang Sha, Hu Nan, P. R. of China;National Laboratory for Parallel & Distributed Processing Chang Sha, Hu Nan, P. R. of China;National Laboratory for Parallel & Distributed Processing Chang Sha, Hu Nan, P. R. of China;National Laboratory for Parallel & Distributed Processing Chang Sha, Hu Nan, P. R. of China

  • Venue:
  • ACSAC'07 Proceedings of the 12th Asia-Pacific conference on Advances in Computer Systems Architecture
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

For target recognition based on biologic vision, an application-specific stream SOC: MASA-MI is described in this paper. MASA-MI consists of several heterogeneous cores, and a stream accelerator core is used to accelerate matching image which consumes the most time in target recognition. We implemented it on Altera EP2S60 FPGA. Result shows the 166MHz MASA-MI provides a peak performance of 585 fps. MASA-MI's performance is an order of magnitude higher than those of today's DSPs such as the Texas Instruments TMS320DM642 (600MHz). On the other hand, the cost is far less than special purpose processors.