| Presentation | 2017-10-12 Performance Evaluation of Gait Recognition by Metric Learning using Joint Intensity Histogram Yushiro Kashimoto, Daigo Muramatsu, Yasushi Makihara, Yasushi Yagi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We evaluate the performance of gait recognition algorithm using metric learning based on log-likelihood ratio of joint intensity histogram (MLLr) method which is robust to carrying status change. For training-based method, it is preferable to prepare training data that are collected in a similar situation to target situation. However, in real situation, multiple situations with different carrying status can be considered, and hence gait recognition algorithm that can be applied to cases with unknown carrying status is expected. In this study, we created training data set and evaluation data sets with some setting about status of carrying baggage by using walking sequence data of 2,070 subjects. And we evaluated the performance of MLLr by applying MLLr method of each training to each evaluation data. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | gait recognition / joint intensity histogram / gait energy image (GEI) |
| Paper # | BioX2017-28 |
| Date of Issue | 2017-10-05 (BioX) |
| Conference Information | |
| Committee | BioX |
|---|---|
| Conference Date | 2017/10/12(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Nobumoto Ohama Memorial Hall |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Biometrics, etc. |
| Chair | Kazuhiko Sumi(AGU) |
| Vice Chair | Hiroshi Takano(Toyama Pref. Univ.) / Hitoshi Imaoka(NEC) |
| Secretary | Hiroshi Takano(AIST) / Hitoshi Imaoka(Fujitsu Labs.) |
| Assistant | Masatsugu Ichino(Univ. of Electro-Comm.) / Naoyuki Takada(Secom) / Norihiro Okui(KDDI Research) |
| Paper Information | |
| Registration To | Technical Committee on Biometrics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Performance Evaluation of Gait Recognition by Metric Learning using Joint Intensity Histogram |
| Sub Title (in English) | |
| Keyword(1) | gait recognition |
| Keyword(2) | joint intensity histogram |
| Keyword(3) | gait energy image (GEI) |
| Keyword(4) | |
| 1st Author's Name | Yushiro Kashimoto |
| 1st Author's Affiliation | Osaka University(Osaka Univ.) |
| 2nd Author's Name | Daigo Muramatsu |
| 2nd Author's Affiliation | Osaka University(Osaka Univ.) |
| 3rd Author's Name | Yasushi Makihara |
| 3rd Author's Affiliation | Osaka University(Osaka Univ.) |
| 4th Author's Name | Yasushi Yagi |
| 4th Author's Affiliation | Osaka University(Osaka Univ.) |
| Date | 2017-10-12 |
| Paper # | BioX2017-28 |
| Volume (vol) | vol.117 |
| Number (no) | BioX-236 |
| Page | pp.pp.17-22(BioX), |
| #Pages | 6 |
| Date of Issue | 2017-10-05 (BioX) |