2026-03-09T21:58:02Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00151077 2025-01-20T16:06:45Z 8512:8654:8655:8540:8545

J-049 見えの変形を学習させた分類木に基づく高精度実時間三次元手指姿勢推定(HIP(3),J分野:ヒューマンコミュニケーション&インタラクション) J-049 Real-Time and Precise 3-D Hand Posture Estimation Based on Decision Tree Trained with Variations of Appearances 宮本, 翔 藤本, 光一 松尾, 直志 島田, 伸敬 白井, 良明 Miyamoto, S. Fujimoto, K. Matsuo, T. Shimada, N. Shirai, Y. Hand posture estimation Image recognition Real-time 3D-posture Hierarchical We propose a method for estimating 3-D hand postures from 2-D images in real-time. The estimation is based on finding the best matched posture from typical postures whose appearances are learned in advance. For high accuracy, conventional methods require high computational cost for comparing an input with many typical postures. In our method, a tree is automatically generated and trained with typical postures and their variations. Efficient search with the tree brings about real-time estimation. We show the effectiveness of our method by some experimental results. conference paper 情報処理学会 2011-09-07 application/pdf 情報科学技術フォーラム講演論文集 3 10 649 654 AA1242354X https://ipsj.ixsq.nii.ac.jp/record/151077/files/KJ00008742650.pdf jpn