Variable window size for stereo image matching based on edge information

dc.contributor.authorEmlek, Alper
dc.contributor.authorPeker, Murat
dc.contributor.authorDilaver, Kamil Fatih
dc.date.accessioned2024-11-07T10:39:28Z
dc.date.available2024-11-07T10:39:28Z
dc.date.issued2017
dc.departmentNiğde Ömer Halisdemir Üniversitesi
dc.description2017 International Artificial Intelligence and Data Processing Symposium, IDAP 2017 -- 16 September 2017 through 17 September 2017 -- Malatya -- 115012
dc.description.abstractFixed window sized methods have usually poor performance compared to variable window size methods due to the noise and context of the scene. In this work, a new variable window size method is proposed for the cost aggregation step of stereo matching. The main idea is to find the depth change regions and match them correctly. Based on the observations, it was seen that the depth changes occurred around the edges of an image. Due to this, the proposed method is designed to determine the window size based on the edge information and match the variable areas of an image. The experimental results are analyzed with the Middlebury stereo evaluation dataset. The proposed method is compared with the sum of absolute differences (SAD) method in different window sizes. © 2017 IEEE.
dc.identifier.doi10.1109/IDAP.2017.8090229
dc.identifier.isbn978-153861880-6
dc.identifier.scopus2-s2.0-85039921468
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/IDAP.2017.8090229
dc.identifier.urihttps://hdl.handle.net/11480/10989
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartofIDAP 2017 - International Artificial Intelligence and Data Processing Symposium
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241106
dc.subjectLocal method
dc.subjectStereo matching
dc.subjectVariable window
dc.titleVariable window size for stereo image matching based on edge information
dc.typeConference Object

Dosyalar