@techreport{oai:ipsj.ixsq.nii.ac.jp:00234310,
 author = {井上, 貴夫 and 深江, 一輝 and 荒井, 研一 and 小林, 透 and Takao, Inoue and Kazuki, Fukae and Kenichi, Arai and Toru, Kobayashi},
 issue = {9},
 month = {May},
 note = {作業者中心でものづくりを行っている中小製造業では作業効率を向上させるため，作業者が行う動作を分析し，最適な作業方法を求め，付加価値のないムダな作業や現状やらなくてはいけない付随作業を減らすことが重要である．具体的な付随作業は部品を取りにいくことや梱包を解く，運搬，モニタ監視などがある．現場の作業者が作業の一部として認識していない，気づいていない付随作業を見える化し，改善するには全体を俯瞰して見る必要がある．この課題に対処するため，本研究では既存の監視カメラを活用する．監視カメラは既に多くの現場に設置されているため，新たな機器の導入が不要で導入コストがかからず，また作業者の動きを客観的に記録することができる監視カメラを利用して作業者の向きや手の位置，設備の位置などの情報を分析し，作業者が気づいていない付随作業を可視化する手法を提案する．具体的には，検査装置を使用した作業に焦点を当て，深層学習と機械学習を組み合わせたアプローチで付随作業の抽出が可能であることが確認された．, In small and medium-sized manufacturing companies that focus on worker-centered production, it is important to analyze the actions of workers to improve operational efficiency, seek optimal working methods, and reduce unnecessary work that doesn't add value, as well as mandatory ancillary tasks. Specific examples of ancillary tasks include fetching parts, unboxing, transport, and monitor surveillance. To visualize and improve ancillary tasks that workers on site may not recognize or notice as part of their work, it is necessary to take an overall view of the process.To address this issue, this study utilizes existing surveillance cameras. As surveillance cameras are already installed in many workplaces, there is no need to introduce new equipment, making it cost-effective. Additionally, the use of surveillance cameras allows for the objective recording of workers' movements. By analyzing information such as the orientation and position of workers' hands, as well as the position of equipment, it is possible to visualize the ancillary tasks that workers may not be aware of. Specifically, focusing on tasks involving inspection equipment, it was confirmed that the combination of deep learning and machine learning approaches can be used to extract ancillary tasks.},
 title = {監視カメラを活用した中小製造業における付随作業の可視化手法の提案},
 year = {2024}
}