Arşiv ve Dokümantasyon Merkezi
Dijital Arşivi

3D human pose estimation from multi-view RGB images

Basit öğe kaydını göster

dc.contributor Graduate Program in Computer Engineering.
dc.contributor.advisor Akarun, Lale.
dc.contributor.advisor Gökberk, Berk.
dc.contributor.author Temiz, Hüseyin.
dc.date.accessioned 2023-03-16T10:04:30Z
dc.date.available 2023-03-16T10:04:30Z
dc.date.issued 2019.
dc.identifier.other CMPE 2019 T46
dc.identifier.uri http://digitalarchive.boun.edu.tr/handle/123456789/12417
dc.description.abstract Recovery of a 3D human pose from cameras has been the subject of intensive research in the last decade. Algorithms that can estimate the 3D pose from a single image have been developed. At the same time, many camera environments have an array of cameras. In this thesis, after aligning the poses obtained from single-view images using Procrustes Analysis, median ltering is utilized to eliminate outliers to nd nal reconstructed 3D body joint coordinates. Experiments performed on the CMU Panoptic, MPI INF 3DHP, and Human3.6M datasets demonstrate that the proposed system achieves accurate 3D body joint reconstructions. Additionally, we observe that camera selection is useful to decrease the system complexity while attaining the same level of reconstruction performance. We also derive that dynamic camera selection has a more signi cant impact on reconstruction accuracy as against static camera selection.
dc.format.extent 30 cm.
dc.publisher Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019.
dc.subject.lcsh Image processing -- Digital techniques.
dc.subject.lcsh Three-dimensional display systems.
dc.title 3D human pose estimation from multi-view RGB images
dc.format.pages xv, 63 leaves ;


Bu öğenin dosyaları

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster

Dijital Arşivde Ara


Göz at

Hesabım