| Presentation | 2016-06-13 Vehicle Classification method based on Deep Neural Networks for Microwave Beat Signals Kohei Yamamoto, Kurato Maeno, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A traffic monitoring system requires environmental resistances against the influence of the weather and the sunshine. A microwave radar is suitable for such outdoor uses because of the nature of the microwave. As one of the traffic monitoring applications using microwave radars, the vehicle classification methods based on the estimation of the height or length profiles of running vehicles had been proposed. However, these methods required the installation of radars on the vertical of the roadway. This condition was a problem of high installation costs. In this paper, we propose the vehicle classification method using a roadside microwave radar based on Deep Neural Networks(DNN) that do not require estimating the vehicle’s height or length profile directly. The proposed DNN model has a feature that integrates the internal outputs of the Convolutional Neural Networks(CNN) and the ones of the radar signal processing in learning. Our approach was compared with the previous study-based DNN model by using the experimental data about the three types of vehicle. Consequently, the proposed DNN model showed better performance in 17.68% of the accuracy difference than previous one and the efficacy against the vehicle classification problem in the case of using a roadside microwave radar. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Microwave radar / deep neural networks / vehicle classification |
| Paper # | PRMU2016-38,SP2016-4,WIT2016-4 |
| Date of Issue | 2016-06-06 (PRMU, SP, WIT) |
| Conference Information | |
| Committee | PRMU / SP / WIT / ASJ-H |
|---|---|
| Conference Date | 2016/6/13(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Eisaku Maeda(NTT) / Kazunori Mano(Shibaura Inst. of Tech.) / Kiyohiko Nunokawa(Tokyo International Univ.) |
| Vice Chair | Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / Hiroki Mori(Utsunomiya Univ.) / Chikamune Wada(Kyushu Inst. of Tech.) |
| Secretary | Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / Hiroki Mori(Kobe Univ.) / Chikamune Wada(Shizuoka Univ.) / (Nagoya Inst. of Tech.) |
| Assistant | Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / Taichi Asami(NTT) / Kei Hashimoto(Nagoya Inst. of Tech.) / Tomohiro Amemiya(NTT) / Takeaki Shionome(Tsukuba Univ. of Tech.) / Manabi Miyagi(Tsukuba Univ. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Speech / Technical Committee on Well-being Information Technology / Auditory Research Meeting |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Vehicle Classification method based on Deep Neural Networks for Microwave Beat Signals |
| Sub Title (in English) | |
| Keyword(1) | Microwave radar |
| Keyword(2) | deep neural networks |
| Keyword(3) | vehicle classification |
| 1st Author's Name | Kohei Yamamoto |
| 1st Author's Affiliation | Oki Electric Industry Co., Ltd.(OKI) |
| 2nd Author's Name | Kurato Maeno |
| 2nd Author's Affiliation | Oki Electric Industry Co., Ltd.(OKI) |
| Date | 2016-06-13 |
| Paper # | PRMU2016-38,SP2016-4,WIT2016-4 |
| Volume (vol) | vol.116 |
| Number (no) | PRMU-89,SP-90,WIT-91 |
| Page | pp.pp.19-24(PRMU), pp.19-24(SP), pp.19-24(WIT), |
| #Pages | 6 |
| Date of Issue | 2016-06-06 (PRMU, SP, WIT) |