A Voxel-based Deep Learning Approach for Point Cloud Semantic Segmentation

dc.contributor.authorDíaz-Medina, Miguelen_US
dc.contributor.authorFuertes-García, José Manuelen_US
dc.contributor.authorOgayar-Anguita, Carlos Javieren_US
dc.contributor.authorLucena, Manuelen_US
dc.contributor.editorCasas, Dan and Jarabo, Adriánen_US
dc.date.accessioned2019-06-25T16:20:48Z
dc.date.available2019-06-25T16:20:48Z
dc.date.issued2019
dc.description.abstractSemantic segmentation has been a research topic in computer vision for decades. This task has become a crucial challenge nowadays due to emergence of new technologies such as autonomous driving. Nonetheless, most existing segmentation methods are not designed for handling the unstructured and irregular nature of 3D point clouds. We propose a voxel-based technique for point cloud data semantic segmentation of 3D point clouds using 3D convolutional neural networks. It uses local voxelizations for learning spatial patterns, and also corrects the imbalance of the data, something very problematic with 3D datasets.en_US
dc.description.sectionheadersShort Papers
dc.description.seriesinformationSpanish Computer Graphics Conference (CEIG)
dc.identifier.doi10.2312/ceig.20191206
dc.identifier.isbn978-3-03868-093-2
dc.identifier.pages73-76
dc.identifier.urihttps://doi.org/10.2312/ceig.20191206
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/ceig20191206
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectComputer Graphics
dc.subjectMachine Learning
dc.titleA Voxel-based Deep Learning Approach for Point Cloud Semantic Segmentationen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
073-076.pdf
Size:
362.22 KB
Format:
Adobe Portable Document Format
Collections