Implementing Image Applications on FPGAs

The Cameron project has developed a language and compiler for mapping image-based applications to field programmable gate arrays (FPGAs). This paper tests this technology on several applications and finds that FPGAs are between 8 and 800 times faster than comparable Pentiums for image based tasks.

• Type: Conference
• Year: 2002
• Where: ICPR
• Authors: A. P. Wim Böhm, Bruce A. Draper, Charles Ross, J. Ross Beveridge, Monica Chawathe
• Keywords: Computer Vision, ICPR 2002, Image Based Tasks, Programmable Gate Arrays