L. Veronese, Lauro Jose Lyrio Junior, Filipe Wall Mutz, Jorcy de Oliveira Neto, Vitor Barbirato
{"title":"Stereo matching with VG-RAM Weightless Neural Networks","authors":"L. Veronese, Lauro Jose Lyrio Junior, Filipe Wall Mutz, Jorcy de Oliveira Neto, Vitor Barbirato","doi":"10.1109/ISDA.2012.6416556","DOIUrl":null,"url":null,"abstract":"Virtual Generalizing Random Access Memory Weightless Neural Networks (VG-RAM WNN) is an effective machine learning technique that offers simple implementation and fast training and test. We examined the performance of VG-RAM WNN on binocular dense stereo matching using the Middlebury Stereo Datasets. Our experimental results showed that, even without tackling occlusions and discontinuities in the stereo image pairs examined, our VG-RAM WNN architecture for stereo matching was able to rank at 114th position in the Middlebury Stereo Evaluation system. This result is promising, because the difference in performance among approaches ranked in distinct positions is very small.","PeriodicalId":370150,"journal":{"name":"2012 12th International Conference on Intelligent Systems Design and Applications (ISDA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 12th International Conference on Intelligent Systems Design and Applications (ISDA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISDA.2012.6416556","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Virtual Generalizing Random Access Memory Weightless Neural Networks (VG-RAM WNN) is an effective machine learning technique that offers simple implementation and fast training and test. We examined the performance of VG-RAM WNN on binocular dense stereo matching using the Middlebury Stereo Datasets. Our experimental results showed that, even without tackling occlusions and discontinuities in the stereo image pairs examined, our VG-RAM WNN architecture for stereo matching was able to rank at 114th position in the Middlebury Stereo Evaluation system. This result is promising, because the difference in performance among approaches ranked in distinct positions is very small.