Difference between revisions of "Publications/blin.22.tpds"

From LRDE

(Created page with "{{Publication | published = true | date = 2022-03-09 | authors = Nicolas Blin, Edwin Carlinet, Florian Lemaitre, Lionel Lacassagne, Thierry Géraud | title = Max-tree Computat...")
 
 
(2 intermediate revisions by the same user not shown)
Line 3: Line 3:
 
| date = 2022-03-09
 
| date = 2022-03-09
 
| authors = Nicolas Blin, Edwin Carlinet, Florian Lemaitre, Lionel Lacassagne, Thierry Géraud
 
| authors = Nicolas Blin, Edwin Carlinet, Florian Lemaitre, Lionel Lacassagne, Thierry Géraud
| title = Max-tree Computation on GPUs
+
| title = Max-Tree Computation on GPUs
 
| journal = IEEE Transactions on Parallel and Distributed Systems
 
| journal = IEEE Transactions on Parallel and Distributed Systems
| abstract = In Mathematical Morphology, the max-tree is a region-based representation that encodes the inclusion relationship of the threshold sets of an image. This tree has been proven useful in numerous image processing applications. For the last decade, works have been led to improve the building time of this structure; mixing algorithmic optimizationsparallel and distributed computing. Nevertheless, there is still no algorithm that takes benefit from the computing power of the massively parallel architectures. In this work, we propose the first GPU algorithm to compute the max-tree. The proposed approach leads to significant speed-ups, and is up to one order of magnitude faster than the current State-of-the-Art parallel CPU algorithms. This work paves the way for a max-tree integration in image processing GPU pipelines and real-time image processing based on Mathematical Morphology. It is also a foundation for porting other image representations from Mathematical Morphology on GPUs.
+
| abstract = In Mathematical Morphology, the max-tree is a region-based representation that encodes the inclusion relationship of the threshold sets of an image. This tree has been proven useful in numerous image processing applications. For the last decade, works have been led to improve the building time of this structure; mixing algorithmic optimizationsparallel and distributed computing. Nevertheless, there is still no algorithm that takes benefit from the computing power of the massively parallel architectures. In this work, we propose the first GPU algorithm to compute the max-tree. The proposed approach leads to significant speed-ups, and is up to one order of magnitude faster than the current State-of-the-Art parallel CPU algorithms. This work paves the way for a max-tree integration in image processing GPU pipelines and real-time image processing based on Mathematical Morphology. It is also a foundation for porting other image representations from Mathematical Morphology on GPUs.
 
| lrdepaper = http://www.lrde.epita.fr/dload/papers/blin.22.tpds.pdf
 
| lrdepaper = http://www.lrde.epita.fr/dload/papers/blin.22.tpds.pdf
 
| lrdeprojects = Olena
 
| lrdeprojects = Olena
Line 12: Line 12:
 
| type = article
 
| type = article
 
| id = blin.22.tpds
 
| id = blin.22.tpds
  +
| identifier = doi:10.1109/TPDS.2022.3158488
 
| bibtex =
 
| bibtex =
 
@Article<nowiki>{</nowiki> blin.22.tpds,
 
@Article<nowiki>{</nowiki> blin.22.tpds,
 
author = <nowiki>{</nowiki>Nicolas Blin and Edwin Carlinet and Florian Lemaitre and
 
author = <nowiki>{</nowiki>Nicolas Blin and Edwin Carlinet and Florian Lemaitre and
 
Lionel Lacassagne and Thierry G\'eraud<nowiki>}</nowiki>,
 
Lionel Lacassagne and Thierry G\'eraud<nowiki>}</nowiki>,
title = <nowiki>{</nowiki>Max-tree Computation on <nowiki>{</nowiki>GPU<nowiki>}</nowiki>s<nowiki>}</nowiki>,
+
title = <nowiki>{</nowiki>Max-Tree Computation on <nowiki>{</nowiki>GPU<nowiki>}</nowiki>s<nowiki>}</nowiki>,
 
journal = <nowiki>{</nowiki>IEEE Transactions on Parallel and Distributed Systems<nowiki>}</nowiki>,
 
journal = <nowiki>{</nowiki>IEEE Transactions on Parallel and Distributed Systems<nowiki>}</nowiki>,
  +
month = mar,
 
year = <nowiki>{</nowiki>2022<nowiki>}</nowiki>,
 
year = <nowiki>{</nowiki>2022<nowiki>}</nowiki>,
 
abstract = <nowiki>{</nowiki>In Mathematical Morphology, the max-tree is a region-based
 
abstract = <nowiki>{</nowiki>In Mathematical Morphology, the max-tree is a region-based
Line 36: Line 38:
 
based on Mathematical Morphology. It is also a foundation
 
based on Mathematical Morphology. It is also a foundation
 
for porting other image representations from Mathematical
 
for porting other image representations from Mathematical
Morphology on GPUs.<nowiki>}</nowiki>
+
Morphology on GPUs.<nowiki>}</nowiki>,
  +
doi = <nowiki>{</nowiki>10.1109/TPDS.2022.3158488<nowiki>}</nowiki>
 
<nowiki>}</nowiki>
 
<nowiki>}</nowiki>
   

Latest revision as of 09:02, 20 April 2022

Abstract

In Mathematical Morphology, the max-tree is a region-based representation that encodes the inclusion relationship of the threshold sets of an image. This tree has been proven useful in numerous image processing applications. For the last decade, works have been led to improve the building time of this structure; mixing algorithmic optimizationsparallel and distributed computing. Nevertheless, there is still no algorithm that takes benefit from the computing power of the massively parallel architectures. In this work, we propose the first GPU algorithm to compute the max-tree. The proposed approach leads to significant speed-ups, and is up to one order of magnitude faster than the current State-of-the-Art parallel CPU algorithms. This work paves the way for a max-tree integration in image processing GPU pipelines and real-time image processing based on Mathematical Morphology. It is also a foundation for porting other image representations from Mathematical Morphology on GPUs.

Documents

Bibtex (lrde.bib)

@Article{	  blin.22.tpds,
  author	= {Nicolas Blin and Edwin Carlinet and Florian Lemaitre and
		  Lionel Lacassagne and Thierry G\'eraud},
  title		= {Max-Tree Computation on {GPU}s},
  journal	= {IEEE Transactions on Parallel and Distributed Systems},
  month		= mar,
  year		= {2022},
  abstract	= {In Mathematical Morphology, the max-tree is a region-based
		  representation that encodes the inclusion relationship of
		  the threshold sets of an image. This tree has been proven
		  useful in numerous image processing applications. For the
		  last decade, works have been led to improve the building
		  time of this structure; mixing algorithmic optimizations,
		  parallel and distributed computing. Nevertheless, there is
		  still no algorithm that takes benefit from the computing
		  power of the massively parallel architectures. In this
		  work, we propose the first GPU algorithm to compute the
		  max-tree. The proposed approach leads to significant
		  speed-ups, and is up to one order of magnitude faster than
		  the current State-of-the-Art parallel CPU algorithms. This
		  work paves the way for a max-tree integration in image
		  processing GPU pipelines and real-time image processing
		  based on Mathematical Morphology. It is also a foundation
		  for porting other image representations from Mathematical
		  Morphology on GPUs.},
  doi		= {10.1109/TPDS.2022.3158488}
}