| Presentation | 2019-03-18 ADL Recognition based on Movement Trajectory of Hand and Object Recognition using Deep Learning for Self-Support Hiroki Kojima, Sho Ooi, Mutsuo Sano, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In our laboratory, we have been studying cognitive rehabilitation for patients with acquired brain injury and dementia based on activities daily living (ADL) such as cooking and clearing. We proposed a method of cleaning behavior estimation using deep learning and conducted experiments of cleaning behavior to patients with acquired brain injury. Specifically, we estimated cleaning behavior using cleaning tools and cleaning area (person's direction). Cleaning tools are recognized by YOLO algorithm, person's directions are recognized by OpenPose algorithm. However, in this method, there were many misrecognition. Therefore, we add movement trajectory of object and hand as feature and describe recognition accuracy of ADL behavior. As a result, accuracy was improved by a method of error correction method which considers time continuity when features are face orientation, hand movement, and object movement. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | ADL / Self Support / YOLO / OpenPose / Living Behavior Recognition |
| Paper # | BioX2018-51,PRMU2018-155 |
| Date of Issue | 2019-03-10 (BioX, PRMU) |
| Conference Information | |
| Committee | PRMU / BioX |
|---|---|
| Conference Date | 2019/3/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Kazuhiko Sumi(AGU) |
| Vice Chair | Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.) / Hitoshi Imaoka(NEC) / Tetsushi Ohki(Shizuoka Univ.) |
| Secretary | Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.) / Hitoshi Imaoka(Fujitsu Labs.) / Tetsushi Ohki(Univ. of Electro-Comm.) |
| Assistant | Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo) / Norihiro Okui(KDDI Research) / Daishi Watabe(Saitama Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Biometrics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | ADL Recognition based on Movement Trajectory of Hand and Object Recognition using Deep Learning for Self-Support |
| Sub Title (in English) | |
| Keyword(1) | ADL |
| Keyword(2) | Self Support |
| Keyword(3) | YOLO |
| Keyword(4) | OpenPose |
| Keyword(5) | Living Behavior Recognition |
| 1st Author's Name | Hiroki Kojima |
| 1st Author's Affiliation | Graduate School of Osaka Institute of Technology(OIT) |
| 2nd Author's Name | Sho Ooi |
| 2nd Author's Affiliation | Ritsumeikan University(Rits) |
| 3rd Author's Name | Mutsuo Sano |
| 3rd Author's Affiliation | Osaka Institute of Technology(OIT) |
| Date | 2019-03-18 |
| Paper # | BioX2018-51,PRMU2018-155 |
| Volume (vol) | vol.118 |
| Number (no) | BioX-512,PRMU-513 |
| Page | pp.pp.131-136(BioX), pp.131-136(PRMU), |
| #Pages | 6 |
| Date of Issue | 2019-03-10 (BioX, PRMU) |