Presentation 2018-08-10
Object Identification with Time Series of Millimeter-wave Radar Information
Takashi Nakamura, Kentaroh Toyoda, Tomoaki Ohtsuki, Osamu Isaji, Kazuaki Hamada, Toshiyuki Miyazaki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Identifying objects with radar is in great demand for avoiding road accidents. Recent research tried to identify moving objects on a road by inputting radar information to a machine learning classifier. In the conventional method, the features used in the machine learning are extracted from the observed radar information with a short time interval. Since the movement of the objects is different depending on the objects, time series information is effective for classification, which has not been exploited before. In this report, we propose a machine learning-based object identification using time series of radar information obtained from the time window that contains series of features. We extract features from a series of features by calculating the mean and variance of object information, i.e., velocity, signal power, and distance. Some experiments were carried out, and the classification performance was evaluated. From the classification results, it is shown that our method outperforms the conventional one of which features are extracted with a short time slice. It is also shown how much each feature contributes to the object identification in our method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) millimeter-wave radar / object identification / automotive system / pedestrian detection
Paper # RCS2018-145
Date of Issue 2018-08-02 (RCS)

Conference Information
Committee SAT / RCS
Conference Date 2018/8/9(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Iwate University
Topics (in Japanese) (See Japanese page)
Topics (in English) Wireless Communications, etc.
Chair Hiroyuki Tsuji(NICT) / Tomoaki Otsuki(Keio Univ.)
Vice Chair Hisashi Sujikai(NHK) / Fumihiro Yamashita(NTT) / Eisuke Fukuda(Fujitsu Labs.) / Satoshi Suyama(NTT DoCoMo) / Fumiaki Maehara(Waseda Univ.)
Secretary Hisashi Sujikai(NTT) / Fumihiro Yamashita(NICT) / Eisuke Fukuda(Hokkaido Univ.) / Satoshi Suyama(NTT) / Fumiaki Maehara
Assistant / Kazushi Muraoka(NTT DOCOMO) / Shinsuke Ibi(Osaka Univ.) / Hiroshi Nishimoto(Mitsubishi Electric) / Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp)

Paper Information
Registration To Technical Committee on Satellite Telecommunications / Technical Committee on Radio Communication Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Object Identification with Time Series of Millimeter-wave Radar Information
Sub Title (in English)
Keyword(1) millimeter-wave radar
Keyword(2) object identification
Keyword(3) automotive system
Keyword(4) pedestrian detection
1st Author's Name Takashi Nakamura
1st Author's Affiliation Keio University(Keio Univ.)
2nd Author's Name Kentaroh Toyoda
2nd Author's Affiliation Keio University(Keio Univ.)
3rd Author's Name Tomoaki Ohtsuki
3rd Author's Affiliation Keio University(Keio Univ.)
4th Author's Name Osamu Isaji
4th Author's Affiliation DENSO TEN Limited(DENSO TEN)
5th Author's Name Kazuaki Hamada
5th Author's Affiliation DENSO TEN Limited(DENSO TEN)
6th Author's Name Toshiyuki Miyazaki
6th Author's Affiliation DENSO TEN Limited(DENSO TEN)
Date 2018-08-10
Paper # RCS2018-145
Volume (vol) vol.118
Number (no) RCS-177
Page pp.pp.75-80(RCS),
#Pages 6
Date of Issue 2018-08-02 (RCS)