Presentation | 2017-03-07 Deep Learning Approach for Moving Object Tracking using Microwave Doppler Signals Motoko Tachibana, Michiyo Hiramoto, Kurato Maeno, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this report, we present a study on tracking using Microwave Doppler Sensor adopting deep learning approach. Measurement of moving object by Microwave Doppler Sensor is more stable than by camera, because it is little susceptible for environment factor, such as weather or lighting. For the purpose, firstly we have to track moving objects which are detected at every sampling time. However, under the condition which two or more objects move at similar speed and are at near positions it is difficult to distinguish them. Therefore, we have adopted deep learning approach for tracking objects in order to solve these difficulties. Concretely, we have created deep convolutional network model for comparison procedure which evaluate whether one of the observed value corresponds with one of the observed value history coordinated by objects. As a result, we achieved high accuracy for the comparison. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Microwave Doppler Sensor / Tracking / Deep Learning |
Paper # | ITS2016-82 |
Date of Issue | 2017-02-28 (ITS) |
Conference Information | |
Committee | ITS / IEE-ITS |
---|---|
Conference Date | 2017/3/7(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kyoto Univ. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Information Processing for ITS, etc. |
Chair | Tomotaka Nagaosa(Kanto Gakuin Univ.) |
Vice Chair | Masahiro Fujii(Utsunomiya Univ.) / Tomotaka Wada(Kansai Univ.) |
Secretary | Masahiro Fujii(Meiji Univ.) / Tomotaka Wada(AIST) |
Assistant | Tetsuya Manabe(Saitama Univ.) / Yanlei Gu(Univ. of Tokyo) / Koichiro Hashiura(Akita Pref. Univ.) |
Paper Information | |
Registration To | Technical Committee on Intelligent Transport Systems Technology / Technical Meeting on Intelligent Transport Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Deep Learning Approach for Moving Object Tracking using Microwave Doppler Signals |
Sub Title (in English) | |
Keyword(1) | Microwave Doppler Sensor |
Keyword(2) | Tracking |
Keyword(3) | Deep Learning |
1st Author's Name | Motoko Tachibana |
1st Author's Affiliation | Oki Electric Industry Co., Ltd.(OKI) |
2nd Author's Name | Michiyo Hiramoto |
2nd Author's Affiliation | Oki Electric Industry Co., Ltd.(OKI) |
3rd Author's Name | Kurato Maeno |
3rd Author's Affiliation | Oki Electric Industry Co., Ltd.(OKI) |
Date | 2017-03-07 |
Paper # | ITS2016-82 |
Volume (vol) | vol.116 |
Number (no) | ITS-502 |
Page | pp.pp.31-35(ITS), |
#Pages | 5 |
Date of Issue | 2017-02-28 (ITS) |