Efficient GPU Asynchronous Implementation of a Watershed Algorithm Based on Cellular Automata

The watershed transform is a widely used method for non-supervised image segmentation, especially suitable for low-contrast images. In this paper we show that an algorithm calculating the watershed transform based on a cellular automaton is a good choice for the most recent GPU architectures, especi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2012 IEEE 10th International Symposium on Parallel and Distributed Processing with Applications s. 79 - 86
Hlavní autoři: Quesada-Barriuso, P., Heras, D. B., Arguello, F.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.07.2012
Témata:
Automata
Cellular Automata
Computer architecture
CUDA
GPU
Graphics processing unit
Image segmentation
Instruction sets
Kernel
Synchronization
Transforms
Watershed transform
ISBN:1467316318, 9781467316316
ISSN:2158-9178
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The watershed transform is a widely used method for non-supervised image segmentation, especially suitable for low-contrast images. In this paper we show that an algorithm calculating the watershed transform based on a cellular automaton is a good choice for the most recent GPU architectures, especially when the synchronization rules are relaxed. In particular we compare a synchronous and an asynchronous implementation of the algorithm. The results show high speedups for both implementations, especially for the asynchronous one, indicating the potential of this kind of algorithms for new architectures based on hundreds of cores.
ISBN:1467316318
9781467316316
ISSN:2158-9178
DOI:10.1109/ISPA.2012.19