https://www.mdu.se/

mdu.sePublications
Planned maintenance
A system upgrade is planned for 24/9-2024, at 12:00-14:00. During this time DiVA will be unavailable.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
The genetic algorithm census transform: evaluation of census windows of different size and level of sparseness through hardware in-the-loop training
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0003-4907-9816
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0002-3425-3837
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0001-7934-6917
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0002-5832-5452
2021 (English)In: Journal of Real-Time Image Processing, ISSN 1861-8200, E-ISSN 1861-8219, no 3, p. 539-559Article in journal (Refereed) Published
Abstract [en]

Stereo correspondence is a well-established research topic and has spawned categories of algorithms combining several processing steps and strategies. One core part to stereo correspondence is to determine matching cost between the two images, or patches from the two images. Over the years several different cost metrics have been proposed, one being the Census Transform (CT). The CT is well proven for its robust matching, especially along object boundaries, with respect to outliers and radiometric differences. The CT also comes at a low computational cost and is suitable for hardware implementation. Two key developments to the CT are non-centric and sparse comparison schemas, to increase matching performance and/or save computational resources. Recent CT algorithms share both traits but are handcrafted, bounded with respect to symmetry, edge lengths and defined for a specific window size. To overcome this, a Genetic Algorithm (GA) was applied to the CT, proposing the Genetic Algorithm Census Transform (GACT), to automatically derive comparison schemas from example data. In this paper, FPGA-based hardware acceleration of GACT, has enabled evaluation of census windows of different size and shape, by significantly reducing processing time associated with training. The experiments show that lateral GACT windows produce better matching accuracy and require less resources when compared to square windows.

Place, publisher, year, edition, pages
SPRINGER HEIDELBERG , 2021. no 3, p. 539-559
Keywords [en]
Census transform, Stereo correspondence, Matching cost metric, Genetic algorithm, Real time, FPGA, SoC, VHDL
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:mdh:diva-50609DOI: 10.1007/s11554-020-00993-wISI: 000545893700001Scopus ID: 2-s2.0-85087560320OAI: oai:DiVA.org:mdh-50609DiVA, id: diva2:1469171
Available from: 2020-09-21 Created: 2020-09-21 Last updated: 2021-06-29Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Ahlberg, CarlLeon, MiguelEkstrand, FredrikEkström, Mikael

Search in DiVA

By author/editor
Ahlberg, CarlLeon, MiguelEkstrand, FredrikEkström, Mikael
By organisation
Embedded Systems
In the same journal
Journal of Real-Time Image Processing
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 220 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf