Presentation | 2021-05-14 A Microwave-based Object Recognition System Using Learning Techniques Viktor Erdelyi, Hamada Rizk, Hirozumi Yamaguchi, Teruo Higashino, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Object recognition has numerous applications including asset tracking, lifestyle analysis, and navigation assistance. However, state-of-the-art approaches tend to require electric objects or tagged objects, or they rely on privacy-sensitive data such as audio or visual images. In this paper, we present a microwave-based object recognition approach. We use two single-antenna software-defined radios to transmit microwave signals through objects and receive them on the opposite side. Then, we recognize the objects using a Random Forest classifier. We evaluated the proposed system using four objects and several microwave frequencies. Using only a 10 ms signal, the system can correctly detect the presence of the object 98.7% of the time, and it can differentiate between different objects 92% of the time. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | uninstrumented object recognition / microwave sensing / software-defined radio / machine learning |
Paper # | CS2021-10 |
Date of Issue | 2021-05-06 (CS) |
Conference Information | |
Committee | CS / CQ |
---|---|
Conference Date | 2021/5/13(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | On-line |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Optical/Wireless Access and Their Integration, Communication Behavior, QoE and Psychology, Assessment / Measurement / Control / Optimization of Communication Quality, Network Services, Wireless Networks, MIMO/Diversity/Multiplexing Techniques, etc. |
Chair | Jun Terada(NTT) / Hideyuki Shimonishi(NEC) |
Vice Chair | Daisuke Umehara(Kyoto Inst. of Tech.) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.) |
Secretary | Daisuke Umehara(Mitsubishi Electric) / Jun Okamoto(NICT) / Takefumi Hiraguri(Doshisha Univ.) |
Assistant | Hiroyuki Saito(OKI) / Takahiro Yamaura(Toshiba) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT) / Ryoichi Kataoka(KDDI Research) |
Paper Information | |
Registration To | Technical Committee on Communication Systems / Technical Committee on Communication Quality |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Microwave-based Object Recognition System Using Learning Techniques |
Sub Title (in English) | |
Keyword(1) | uninstrumented object recognition |
Keyword(2) | microwave sensing |
Keyword(3) | software-defined radio |
Keyword(4) | machine learning |
1st Author's Name | Viktor Erdelyi |
1st Author's Affiliation | Osaka University(Osaka Univ.) |
2nd Author's Name | Hamada Rizk |
2nd Author's Affiliation | Osaka University(Osaka Univ.) |
3rd Author's Name | Hirozumi Yamaguchi |
3rd Author's Affiliation | Osaka University(Osaka Univ.) |
4th Author's Name | Teruo Higashino |
4th Author's Affiliation | Osaka University(Osaka Univ.) |
Date | 2021-05-14 |
Paper # | CS2021-10 |
Volume (vol) | vol.121 |
Number (no) | CS-14 |
Page | pp.pp.37-42(CS), |
#Pages | 6 |
Date of Issue | 2021-05-06 (CS) |