@techreport{oai:ipsj.ixsq.nii.ac.jp:00077289, author = {齋藤, 俊太 and 河内, まき子 and 持丸, 正明 and 青木, 義満 and Shunta, Saito and Makiko, Kochi and Masaaki, Mochimaru and Yoshimitsu, Aoki}, issue = {15}, month = {Aug}, note = {本稿では,身体の輪郭を正確に反映したシルエットが取得可能な理想条件下において正面および側面から撮影した 2 枚の人物シルエット画像から体幹部領域を手動抽出後,対象人物の体幹部 3 次元形状をモデルベースに推定する手法を述べる.事前に多数の被験者に対し全身ボディスキャナによる全身形状計測を行い,相同化の後主成分分析を行って得た任意体型が合成可能なモデルを用いる.このモデルと入力をシルエット同士で比較し,モデルの変形パラメータを最適化することで形状推定を行う., This paper attempts to estimate a 3D shape of human torso from 2 pictures which are front and side silhouette of a subject. Our method assumes that input pictures have accurate contours of a subject's body. And regions of torsos are extracted manually from input pictures. We use a deformable body model for estimation. This model is generated by Principal Component Analysis to a homologous model database which is made of whole body scanned data. A result shape is computed by optimizing some deformation parameters of the model with comparing model's silhouettes and input silhouettes.}, title = {モデルベース人体体幹部3次元形状推定}, year = {2011} }