Learning disentangled representations of point clouds via alpha complexes for 3D shape classification

Show simple item record

dc.contributor.advisor Poovvancheri, Jiju
dc.creator Agowun, Altaf M.
dc.date.accessioned 2024-05-09T13:24:00Z
dc.date.available 2024-05-09T13:24:00Z
dc.date.issued 2024-04-26
dc.identifier.uri http://library2.smu.ca/xmlui/handle/01/31926
dc.description 1 online resource (viii, 50 pages) : illustrations (some colour), charts (some colour), graphs (some colour)
dc.description Includes abstract.
dc.description Includes bibliographical references (pages 45-50).
dc.description.abstract Three-dimensional computer vision tasks have gained much attention in recent times, both in academic and industrial research. One of the key tasks of 3D computer vision is object classification. Various approaches based on the representations (e.g., point clouds, voxels, multi-view images and graphs) of the objects have been put forward for object classification. Recently, few works have used graph neural network for point cloud classification and have achieved promising results. In this thesis, we explore the use of a dual-stream graph neural network combining the alpha complexes constructed on the feature and non-feature regions of the point cloud object. The disentangled representation of the point cloud into feature and non-feature regions is achieved through a gradient structure analysis procedure and a Corner and Edge detection technique. Our experiments on ModelNet40 benchmark dataset indicate that the proposed graph-based method achieves higher or comparable accuracy to other state-of-the-art methods. en_CA
dc.description.provenance Submitted by Greg Hilliard (greg.hilliard@smu.ca) on 2024-05-09T13:24:00Z No. of bitstreams: 1 Agowun_Altaf_Honours_2024.pdf: 30256512 bytes, checksum: 48eb7520ae9d8bd73e277d7498c77633 (MD5) en
dc.description.provenance Made available in DSpace on 2024-05-09T13:24:00Z (GMT). No. of bitstreams: 1 Agowun_Altaf_Honours_2024.pdf: 30256512 bytes, checksum: 48eb7520ae9d8bd73e277d7498c77633 (MD5) Previous issue date: 2024-04-26 en
dc.language.iso en en_CA
dc.publisher Halifax, N.S. : Saint Mary's University
dc.title Learning disentangled representations of point clouds via alpha complexes for 3D shape classification en_CA
dc.type Text en_CA
thesis.degree.name Bachelor of Science (Honours Computing Science)
thesis.degree.level Undergraduate
thesis.degree.discipline Mathematics and Computing Science
thesis.degree.grantor Saint Mary's University (Halifax, N.S.)
 Find Full text

Files in this item

 
 

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Browse

My Account