Methods and Tools for High-Resolution Imaging
Film and video sequences are increasingly being digitised, allowing image processing operations to be applied to them in the digital domain. For film in particular, images are digitised at the limit of available scanners: each frame may contain 3000 by 2000 pixels, with 16 bits per colour channel. We investigate the consequences of working with these high-resolution images on FPGAs. We consider template matching and related algorithms, and derive a performance model to establish bounds on performance and to predict which optimisations may be fruitful. An architecture generator has been developed which can generate optimised implementations given image resolution, the FPGA platform architecture, and a description of the image processing algorithm.
Unable to display preview. Download preview PDF.
- 1.Celoxica DK1 website, http://www.celoxica.com/products/tools/dk.asp
- 2.Digital Mammography Database website, www.wiau.man.ac.uk/services/MIAS/MIASfaq.html
- 3.Diniz, P., Park, J.: Automatic Synthesis of Data Storage and Control Structures for FPGA-based Computing Engines. In: Proceedings FCCM, IEEE, Los Alamitos (2000)Google Scholar
- 4.Gause, J., Cheung, P.Y.K., Luk, W.: Reconfigurable Shape-Adaptive Template Matching Architectures. In: Proceedings FCCM, IEEE, Los Alamitos (2002)Google Scholar
- 5.Nikolaidis, N., Pitas, I.: 3-D Image Processing Algorithms. John Wiley, Chichester (2001)Google Scholar
- 6.Park, J., Diniz, P.: An External Memory Interface for FPGA-Based Computing Engines. In: Proceedings FCCM, IEEE, Los Alamitos (2001)Google Scholar
- 7.Kurt Rossman Laboratories web site, www-radiology.uchicago.edu/krl/imgquali.htm
- 8.Weinhardt, M., Luk, W.: Memory Access Optimisation for Reconfigurable Systems. In: IEE Proc. Comput. Digit. Tech., IEE, vol. 148(3) (May 2001)Google Scholar