A Computationally Efficient Pipeline for 3d Point Cloud Reconstruction from Video Sequences

dc.contributor.authorChang, Chih-Hsiang
dc.contributor.authorKehtarnavaz, Nasser
dc.contributor.utdAuthorChang, Chih-Hsiang
dc.contributor.utdAuthorKehtarnavaz, Nasser
dc.date.accessioned2019-06-28T18:11:08Z
dc.date.available2019-06-28T18:11:08Z
dc.date.created2018-05-14
dc.descriptionFull text access from Treasures at UT Dallas is restricted to current UTD affiliates.
dc.description.abstractThis paper presents a computationally efficient pipeline to achieve 3D point cloud reconstruction from video sequences. This pipeline involves a key frame selection step to improve the computational efficiency by generating reliable depth information from pair-wise frames. An outlier removal step is then applied in order to further improve the computational efficiency. The reconstruction is achieved based on a new absolute camera pose recovery approach in a computationally efficient manner. This pipeline is devised for both sparse and dense 3D reconstruction. The results obtained from video sequences exhibit higher computational efficiency and lower re-projection errors of the introduced pipeline compared to the existing pipelines.
dc.description.departmentErik Jonsson School of Engineering and Computer Science
dc.identifier.bibliographicCitationChang, C. -H, and N. Kehtarnavaz. 2018. "A computationally efficient pipeline for 3D point cloud reconstruction from video sequences." Proceedings of SPIE - The International Society for Optical Engineering 10670, doi:10.1117/12.2302674
dc.identifier.isbn9781510618510
dc.identifier.urihttps://hdl.handle.net/10735.1/6623
dc.identifier.volume10670
dc.language.isoen
dc.publisherSPIE
dc.relation.urihttp://dx.doi.org/10.1117/12.2302674
dc.rights©2018 SPIE
dc.source.journalProceedings of SPIE - The International Society for Optical Engineering
dc.subjectCameras
dc.subjectPipelining (Electronics)
dc.subjectThree-dimensional display systems
dc.subjectVideo recording
dc.subjectSignal processing
dc.subjectImage reconstruction
dc.titleA Computationally Efficient Pipeline for 3d Point Cloud Reconstruction from Video Sequences
dc.type.genrearticle

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
JECS-4163-279644.02-LINK.pdf
Size:
165.04 KB
Format:
Adobe Portable Document Format
Description:
Link to Article