Parallel Khoros: A Software Tool for Parallel Image Processing

The main objective of this project is to build a software tool for simplifying parallel programming of image processing applications by utilizing existing high performance image processing and numerical computing libraries such as ScaLAPACK. Our project uses the Khoros visual programming language to represent computer vision and image processing (CVIP) operations and the system provides an automatic partitioning and scheduling scheme for mapping tasks and images onto distributed memory multiprocessors.

Publications:

C. Lee,Y.-F., Wang, T. Yang, Global Optimization for Mapping Parallel Image Processing Tasks, in Journal of Parallel and Distributed Computing}. V. 45, 29-45, 1997.

C. Lee, Y.-F., Wang, and T. Yang, Static Global Scheduling for Optimal Computer Vision and Image Processing Operations on Distributed-Memory Multiprocessors, Proc. of 6th International Conference on Computer Analysis of Images and Patterns, Sept. 1995. pp.920-925.

C. Lee, T. Yang, and Y.-F. Wang, Partitioning and Scheduling for Image Processing Operations, , Proc. of Seventh IEEE Symposium on Parallel and Distributed Processing, Texas, Oct. 1995. pp 86-90.

Contact persons: Cheolwhan Lee (PhD 1997. Currently with Oracle), Yuan-Fang Wang , Tao Yang

Back to CS Department Home Page