1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | mtc-m16c.sid.inpe.br |
Holder Code | isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S |
Identifier | 8JMKD3MGP8W/3BTFE7P |
Repository | sid.inpe.br/mtc-m18/2012/05.18.13.11 |
Last Update | 2012:05.18.13.11.07 (UTC) administrator |
Metadata Repository | sid.inpe.br/mtc-m18/2012/05.18.13.11.07 |
Metadata Last Update | 2018:06.04.03.55.40 (UTC) administrator |
ISBN | 978-85-17-00059-1 |
Citation Key | HappFeitBentFari:2012:PaImSe |
Title | A parallel image segmentation algorithm on GPUS |
Format | On-line. |
Year | 2012 |
Access Date | 2024, Apr. 29 |
Secondary Type | PRE CI |
Number of Files | 1 |
Size | 586 KiB |
|
2. Context | |
Author | 1 Happ, Patrick 2 Feitosa, Raul 3 Bentes, Cristiana 4 Farias, Ricardo |
Author e-Mail Address | 1 patrick@ele.puc-rio.br 2 raul@ele.puc-rio.br 3 cris@eng.uerj.br 4 rfarias@cos.ufrj.br |
Editor | Feitosa, Raul Queiroz Costa, Gilson Alexandre Ostwald Pedro da Almeida, Cláudia Maria de Fonseca, Leila Maria Garcia Kux, Hermann Johann Heinrich |
e-Mail Address | wanderf@dsr.inpe.br |
Conference Name | International Conference on Geographic Object-Based Image Analysis, 4 (GEOBIA). |
Conference Location | Rio de Janeiro |
Date | May 7-9, 2012 |
Publisher | Instituto Nacional de Pesquisas Espaciais (INPE) |
Publisher City | São José dos Campos |
Pages | 580-585 |
Book Title | Proceedings |
Organization | Instituto Nacional de Pesquisas Espaciais (INPE) |
History (UTC) | 2012-05-18 13:11:07 :: wanderf@dsr.inpe.br -> administrator :: 2012-05-30 13:45:31 :: administrator -> wanderf@dsr.inpe.br :: 2012 2012-06-01 15:12:45 :: wanderf@dsr.inpe.br -> marciana :: 2012 2012-06-12 14:28:25 :: marciana -> seki@dsr.inpe.br :: 2012 2012-06-13 15:55:31 :: seki@dsr.inpe.br -> marciana :: 2012 2012-06-14 15:03:57 :: marciana -> administrator :: 2012 2018-06-04 03:55:40 :: administrator -> :: 2012 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Keywords | Image Segmentation Parallel Processing GPU |
Abstract | Image segmentation is a computationally expensive task that continuously presents performance challenges due to the increasing volume of available high resolution remote sensing images. Nowadays, Graphics Processing Units (GPUs) are emerging as an attractive computing platform for general purpose computations due to their extremely high floating-point processing performance and their comparatively low cost. In the image analysis context, the use of GPUs can accelerate the segmentation process. This work presents a parallel implementation of a region growing algorithm for GPUs. The parallel algorithm is based on processing each pixel as a different thread so as to take advantage of the fine-grain parallel capability of the GPU. In addition to the parallel algorithm, the paper also suggests a modification to the heterogeneity computation that improves the segmentation performance. The experiments results demonstrate that the parallel algorithm achieve significant performance gains, running up to 6.8 times faster than the sequential approach. |
Area | SRE |
Type | Segmentation |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | there are no files |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/8JMKD3MGP8W/3BTFE7P |
zipped data URL | http://urlib.net/zip/8JMKD3MGP8W/3BTFE7P |
Language | en |
Target File | 162.pdf |
User Group | administrator wanderf@dsr.inpe.br |
Visibility | shown |
|
5. Allied materials | |
Mirror Repository | urlib.net/www/2011/03.29.20.55 |
Host Collection | sid.inpe.br/mtc-m18@80/2008/03.17.15.17 |
|
6. Notes | |
Empty Fields | affiliation archivingpolicy archivist callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition group issn label lineage mark nextedition nexthigherunit notes numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark serieseditor shorttitle sponsor tertiarymark tertiarytype url versiontype volume |
|