dc.contributor.author |
Loke, Seng Cheong |
|
dc.contributor.author |
MacDonald, Bruce A |
|
dc.contributor.author |
Parsons, Matthew |
|
dc.contributor.author |
Wünsche, Burkhard Claus |
|
dc.date.accessioned |
2022-08-22T03:25:57Z |
|
dc.date.available |
2022-08-22T03:25:57Z |
|
dc.date.issued |
2021-05-22 |
|
dc.identifier.citation |
(2021). Journal of Real-Time Image Processing, 18(6), 2361-2376. |
|
dc.identifier.issn |
1861-8200 |
|
dc.identifier.uri |
https://hdl.handle.net/2292/60884 |
|
dc.description.abstract |
Segmentation of an image into superpixel clusters is a necessary part of many imaging pathways. In this article, we describe a new routine for superpixel image segmentation (F-DBSCAN) based on the DBSCAN algorithm that is six times faster than previous existing methods, while being competitive in terms of segmentation quality and resistance to noise. The gains in speed are achieved through efficient parallelization of the cluster search process by limiting the size of each cluster thus enabling the processes to operate in parallel without duplicating search areas. Calculations are performed in large consolidated memory buffers which eliminate fragmentation and maximize memory cache hits thus improving performance. When tested on the Berkeley Segmentation Dataset, the average processing speed is 175 frames/s with a Boundary Recall of 0.797 and an Achievable Segmentation Accuracy of 0.944. |
|
dc.language |
en |
|
dc.publisher |
Springer Nature |
|
dc.relation.ispartofseries |
Journal of Real-Time Image Processing |
|
dc.rights |
Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. |
|
dc.rights.uri |
https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm |
|
dc.subject |
Biomedical Imaging |
|
dc.subject |
Networking and Information Technology R&D |
|
dc.subject |
Science & Technology |
|
dc.subject |
Technology |
|
dc.subject |
Computer Science, Artificial Intelligence |
|
dc.subject |
Engineering, Electrical & Electronic |
|
dc.subject |
Imaging Science & Photographic Technology |
|
dc.subject |
Computer Science |
|
dc.subject |
Engineering |
|
dc.subject |
Computational photography |
|
dc.subject |
Concurrent algorithms |
|
dc.subject |
DBSCAN |
|
dc.subject |
Image segmentation |
|
dc.subject |
Memory allocation |
|
dc.subject |
Superpixels |
|
dc.title |
Accelerated superpixel image segmentation with a parallelized DBSCAN algorithm |
|
dc.type |
Journal Article |
|
dc.identifier.doi |
10.1007/s11554-021-01128-5 |
|
pubs.issue |
6 |
|
pubs.begin-page |
2361 |
|
pubs.volume |
18 |
|
dc.date.updated |
2022-07-22T04:52:23Z |
|
dc.rights.holder |
Copyright: The authors |
en |
pubs.author-url |
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000652934700001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=6e41486220adb198d0efde5a3b153e7d |
|
pubs.end-page |
2376 |
|
pubs.publication-status |
Published |
|
dc.rights.accessrights |
http://purl.org/eprint/accessRights/RestrictedAccess |
en |
pubs.subtype |
Article |
|
pubs.subtype |
Journal |
|
pubs.elements-id |
855336 |
|
pubs.org-id |
Engineering |
|
pubs.org-id |
Medical and Health Sciences |
|
pubs.org-id |
Science |
|
pubs.org-id |
School of Computer Science |
|
pubs.org-id |
Nursing |
|
pubs.org-id |
Department of Electrical, Computer and Software Engineering |
|
dc.identifier.eissn |
1861-8219 |
|
pubs.record-created-at-source-date |
2022-07-22 |
|
pubs.online-publication-date |
2021-12 |
|