| Presentation | 2016-03-24 Multi-User Localization Based on Trajectory Group Optimization Considering Characteristics of Individuals and Devices Kenji Imanishi, Yoshimichi Ito, Noboru Babaguchi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently, a method for multi-user localization in indoor environment using textit{trajectory group optimization} has been proposed. This method simultaneously corrects trajectories of multiple users by optimizing a cost function when two measurements are observed: the distance between users estimated from received signal strength obtained by Bluetooth, and the user position estimated by static cameras. However, this method assumes that strides of all users are the same and that there is no individual difference on all devices. In this paper, we aim to improve the localization accuracy by introducing the pre-learning step before the estimation step, in which the stride of each user, as well as the declination of each device, is estimated by user's trajectory at a part of the environment. We consider a suitable movement at the pre-learning step through experiments, and evaluate the effectiveness of the proposed method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | learning / trajectory / localization / optimization |
| Paper # | BioX2015-44,PRMU2015-167 |
| Date of Issue | 2016-03-17 (BioX, PRMU) |
| Conference Information | |
| Committee | PRMU / BioX |
|---|---|
| Conference Date | 2016/3/24(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Eisaku Maeda(NTT) / Masakatsu Nishigaki(Shizuoka Univ.) |
| Vice Chair | Shuji Senda(NEC) / Seiichi Uchida(Kyushu Univ.) / Kazuhiko Sumi(Aoyama Gakuin Univ.) / Akira Otsuka(AIST) |
| Secretary | Shuji Senda(Mie Univ.) / Seiichi Uchida(DENSO IT Lab.) / Kazuhiko Sumi(Toyama Pref. Univ.) / Akira Otsuka(NEC) |
| Assistant | Kazuaki Kondo(Kyoto Univ.) / Akisato Kimura(NTT) / Tetsushi Ohki(AIST) / Nobuyuki Nishiuchi(Tokyo Metropolitan Univ.) |
| 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) | Multi-User Localization Based on Trajectory Group Optimization Considering Characteristics of Individuals and Devices |
| Sub Title (in English) | |
| Keyword(1) | learning |
| Keyword(2) | trajectory |
| Keyword(3) | localization |
| Keyword(4) | optimization |
| 1st Author's Name | Kenji Imanishi |
| 1st Author's Affiliation | Osaka University(Osaka Univ.) |
| 2nd Author's Name | Yoshimichi Ito |
| 2nd Author's Affiliation | Osaka Electro-Communication University(OECU) |
| 3rd Author's Name | Noboru Babaguchi |
| 3rd Author's Affiliation | Osaka University(Osaka Univ.) |
| Date | 2016-03-24 |
| Paper # | BioX2015-44,PRMU2015-167 |
| Volume (vol) | vol.115 |
| Number (no) | BioX-516,PRMU-517 |
| Page | pp.pp.19-24(BioX), pp.19-24(PRMU), |
| #Pages | 6 |
| Date of Issue | 2016-03-17 (BioX, PRMU) |