Name
Abstract | ||
|---|---|---|
The watershed transform is a very powerful segmentation tool which comes directly from the idea of watershed line in geohydrology. It has proved its efficiency in many computer vision application fields. This paper presents a new implementation of the watershed which is optimal according to computation time. The flooding algorithm is reminded. Then, a massively parallel cellular automaton is proposed to propagate data using this approach. We discuss the pros and cons of a hardware implementation and give an example of application. A comparison between the results obtained and theoretical limit cases is also presented. |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/ASAP.1997.606811 | ASAP |
Keywords | Field | DocType |
parallel implementation,theoretical limit case,cellular automaton,new implementation,flooding algorithm,watershed line,powerful segmentation tool,hardware implementation,computer vision application field,cellular automata,water resources,watershed transform,application software,hardware,parallel algorithms,very large scale integration,pixel,geohydrology,automata,computer vision,image segmentation,computational complexity | Cellular automaton,Massively parallel,Computer science,Segmentation,Parallel computing,Watershed,Image segmentation,Flooding algorithm,Computational complexity theory,Computation | Conference |
ISSN | ISBN | Citations |
1063-6862 | 0-8186-7958-1 | 3 |
PageRank | References | Authors |
0.44 | 11 | 1 |