| Presentation | 2018-03-08 Accuracy Evaluation of Machine Learning-based Human Anomaly Motion Recognition using Human Pose Estimation Kengo Ichihara, Masaru Takeuchi, Kenji Kanai, Jiro Katto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we evaluate recognition accuracy of human motion by using a state-of-the-art pose estimation method called “OpenPose”. We construct 3D character models as a training data by using 3D modeling software and train the data by using Support Vector Model (SVM), Neural Network (NN), Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN). Evaluation results indicate that NN provides the highest recognition accuracy among all methods in case of using our data set. In addition, especially in CNN case, we validate that not only use of the image, but also use of temporal information will contribute to accuracy improvement. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Pose estimation / Machine learning / Action recognition |
| Paper # | IMQ2017-41,IE2017-133,MVE2017-83 |
| Date of Issue | 2018-03-01 (IMQ, IE, MVE) |
| Conference Information | |
| Committee | CQ / MVE / IE / IMQ |
|---|---|
| Conference Date | 2018/3/8(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Okinawa Industry Support Center |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Five Senses Media, Cooking and Eating Activities Media, Multimedia, Media Experience, Video Encoding, Image Media Quality, Network Quality and Reliability, etc. (Co-sponsor: Technical Committee on Multimedia on Cooking and Eating Activities (CEA)) |
| Chair | Takanori Hayashi(Hiroshima Inst. of Tech.) / Yoshinari Kameda(Univ. of Tsukuba) / Takayuki Hamamoto(Tokyo Univ. of Science) / Kenji Sugiyama(Seikei Univ.) |
| Vice Chair | Hideyuki Shimonishi(NEC) / Jun Okamoto(NTT) / Kenji Mase(Nagoya Univ.) / Kazuya Kodama(NII) / Hideaki Kimata(NTT) / Toshiya Nakaguchi(Chiba Univ.) / Mitsuru Maeda(Canon) |
| Secretary | Hideyuki Shimonishi(NTT) / Jun Okamoto(Keio Univ.) / Kenji Mase(Kyoto Univ.) / Kazuya Kodama(NTT) / Hideaki Kimata(Kyushu Univ.) / Toshiya Nakaguchi(Nagoya Univ.) / Mitsuru Maeda(KDDI Research) |
| Assistant | Kenko Ota(Nippon Inst. of Tech.) / Norihiro Fukumoto(KDDI Research Inc.) / Ryo Yamamoto(UEC) / Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(NTT) / Yasutaka Matsuo(NHK) / Kazuya Hayase(NTT) / Masaru Tsuchida(NTT) / Gosuke Ohashi(Shizuoka Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Communication Quality / Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Engineering / Technical Committee on Image Media Quality |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Accuracy Evaluation of Machine Learning-based Human Anomaly Motion Recognition using Human Pose Estimation |
| Sub Title (in English) | |
| Keyword(1) | Pose estimation |
| Keyword(2) | Machine learning |
| Keyword(3) | Action recognition |
| 1st Author's Name | Kengo Ichihara |
| 1st Author's Affiliation | Waseda University(Waseda Univ.) |
| 2nd Author's Name | Masaru Takeuchi |
| 2nd Author's Affiliation | Waseda University(Waseda Univ.) |
| 3rd Author's Name | Kenji Kanai |
| 3rd Author's Affiliation | Waseda University(Waseda Univ.) |
| 4th Author's Name | Jiro Katto |
| 4th Author's Affiliation | Waseda University(Waseda Univ.) |
| Date | 2018-03-08 |
| Paper # | IMQ2017-41,IE2017-133,MVE2017-83 |
| Volume (vol) | vol.117 |
| Number (no) | IMQ-483,IE-484,MVE-485 |
| Page | pp.pp.89-94(IMQ), pp.89-94(IE), pp.89-94(MVE), |
| #Pages | 6 |
| Date of Issue | 2018-03-01 (IMQ, IE, MVE) |