The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kertas kerja ini membentangkan kaedah untuk menangkap gerakan manusia tanpa penanda menggunakan satu kamera. Ia menggunakan penapisan berasaskan pokok untuk menyebarkan taburan kebarangkalian dengan cekap ke atas pose model badan 3D. Vektor pose dan bentuk yang berkaitan disusun dalam pokok, yang dibina oleh pengelompokan berpasangan hierarki, untuk menilai dengan cekap kemungkinan dalam setiap bingkai. Fungsi kemungkinan baharu berdasarkan padanan siluet dicadangkan yang meningkatkan anggaran pose bahagian badan yang lebih kurus, iaitu anggota badan. Model dinamik mengambil kira oklusi diri dengan meningkatkan varians bahagian badan yang tersumbat, sekali gus membolehkan pemulihan apabila bahagian badan itu muncul semula. Kami membentangkan dua aplikasi kaedah kami yang berfungsi dalam masa nyata pada Enjin Jalur Lebar SelTM: permainan komputer dan aplikasi pakaian maya.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Ryuzo OKADA, Bjorn STENGER, "A Single Camera Motion Capture System for Human-Computer Interaction" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 7, pp. 1855-1862, July 2008, doi: 10.1093/ietisy/e91-d.7.1855.
Abstract: This paper presents a method for markerless human motion capture using a single camera. It uses tree-based filtering to efficiently propagate a probability distribution over poses of a 3D body model. The pose vectors and associated shapes are arranged in a tree, which is constructed by hierarchical pairwise clustering, in order to efficiently evaluate the likelihood in each frame. A new likelihood function based on silhouette matching is proposed that improves the pose estimation of thinner body parts, i.e. the limbs. The dynamic model takes self-occlusion into account by increasing the variance of occluded body-parts, thus allowing for recovery when the body part reappears. We present two applications of our method that work in real-time on a Cell Broadband EngineTM: a computer game and a virtual clothing application.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.7.1855/_p
Salinan
@ARTICLE{e91-d_7_1855,
author={Ryuzo OKADA, Bjorn STENGER, },
journal={IEICE TRANSACTIONS on Information},
title={A Single Camera Motion Capture System for Human-Computer Interaction},
year={2008},
volume={E91-D},
number={7},
pages={1855-1862},
abstract={This paper presents a method for markerless human motion capture using a single camera. It uses tree-based filtering to efficiently propagate a probability distribution over poses of a 3D body model. The pose vectors and associated shapes are arranged in a tree, which is constructed by hierarchical pairwise clustering, in order to efficiently evaluate the likelihood in each frame. A new likelihood function based on silhouette matching is proposed that improves the pose estimation of thinner body parts, i.e. the limbs. The dynamic model takes self-occlusion into account by increasing the variance of occluded body-parts, thus allowing for recovery when the body part reappears. We present two applications of our method that work in real-time on a Cell Broadband EngineTM: a computer game and a virtual clothing application.},
keywords={},
doi={10.1093/ietisy/e91-d.7.1855},
ISSN={1745-1361},
month={July},}
Salinan
TY - JOUR
TI - A Single Camera Motion Capture System for Human-Computer Interaction
T2 - IEICE TRANSACTIONS on Information
SP - 1855
EP - 1862
AU - Ryuzo OKADA
AU - Bjorn STENGER
PY - 2008
DO - 10.1093/ietisy/e91-d.7.1855
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2008
AB - This paper presents a method for markerless human motion capture using a single camera. It uses tree-based filtering to efficiently propagate a probability distribution over poses of a 3D body model. The pose vectors and associated shapes are arranged in a tree, which is constructed by hierarchical pairwise clustering, in order to efficiently evaluate the likelihood in each frame. A new likelihood function based on silhouette matching is proposed that improves the pose estimation of thinner body parts, i.e. the limbs. The dynamic model takes self-occlusion into account by increasing the variance of occluded body-parts, thus allowing for recovery when the body part reappears. We present two applications of our method that work in real-time on a Cell Broadband EngineTM: a computer game and a virtual clothing application.
ER -