Show simple item record

dc.contributor.authorRangel, José Carlos
dc.contributor.authorMorell, Vicente
dc.contributor.authorCazorla, Miguel
dc.contributor.authorOrts-Escolano, Sergio
dc.contributor.authorGarcía-Rodríguez, José
dc.date.accessioned2019-08-30T16:10:28Z
dc.date.available2019-08-30T16:10:28Z
dc.date.issued2016-04-26
dc.identifierhttps://link.springer.com/article/10.1007/s10044-016-0546-y
dc.identifier.otherhttps://doi.org/10.1007/s10044-016-0546-y
dc.identifier.urihttp://ridda2.utp.ac.pa/handle/123456789/6475
dc.descriptionObject recognition in 3D scenes is a research field in which there is intense activity guided by the problems related to the use of 3D point clouds. Some of these problems are influenced by the presence of noise in the cloud that reduces the effectiveness of a recognition process. This work proposes a method for dealing with the noise present in point clouds by applying the growing neural gas (GNG) network filtering algorithm. This method is able to represent the input data with the desired number of neurons while preserving the topology of the input space. The GNG obtained results which were compared with a Voxel grid filter to determine the efficacy of our approach. Moreover, since a stage of the recognition process includes the detection of keypoints in a cloud, we evaluated different keypoint detectors to determine which one produces the best results in the selected pipeline. Experiments show how the GNG method yields better recognition results than other filtering algorithms when noise is present.en_US
dc.description.abstractObject recognition in 3D scenes is a research field in which there is intense activity guided by the problems related to the use of 3D point clouds. Some of these problems are influenced by the presence of noise in the cloud that reduces the effectiveness of a recognition process. This work proposes a method for dealing with the noise present in point clouds by applying the growing neural gas (GNG) network filtering algorithm. This method is able to represent the input data with the desired number of neurons while preserving the topology of the input space. The GNG obtained results which were compared with a Voxel grid filter to determine the efficacy of our approach. Moreover, since a stage of the recognition process includes the detection of keypoints in a cloud, we evaluated different keypoint detectors to determine which one produces the best results in the selected pipeline. Experiments show how the GNG method yields better recognition results than other filtering algorithms when noise is present.en_US
dc.language.isoengen_US
dc.publisherPattern Analysis and Applicationsen_US
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject3D object recognitionen_US
dc.subjectGrowing neural gasen_US
dc.subjectKeypoint detectionen_US
dc.titleObject recognition in noisy RGB-D data using GNGen_US
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record