Presentation | 2023-01-19 [Short Paper] An experimental study on the transition of camera-based human localization to CSI sensing Kanare Kodera, Shoki Ohta, Takayuki Nishio, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Wi-Fi sensing, represented by CSI (channel state information) sensing~cite{CSIsurvey}, has attracted much attention. Compared to sensing using cameras and other devices, CSI does not include privacy information such as a person's face or appearance. Moreover, its implementation cost is cheaper than the camera and LiDARs since Wi-Fi access points are already installed in many environments, and the price of Wi-Fi devices is cheaper. However, achieving sensing accuracy comparable to that of cameras requires adopting machine learning models to their deployed environment well. In this paper, we propose a training framework for a Wi-Fi sensing model using camera-based sensing as a teacher toward the transition from the camera-based sensing to Wi-Fi sensing. The focus of this study is to determine how we should design tasks and deploy CSI devices to achieve accuracy comparable to that of sensing with cameras. To this end, this study experimentally shows the relationship between Wi-Fi sensing accuracy and the number and placement of CSI measurement devices when cameras are used as teachers. Experiments on predicting the location of a person from CSI using the person detection results of YOLOv7~cite{YOLOv7} as a teacher have shown that the prediction accuracy is high when a person only goes back and forth in the vicinity of the line-of-sight communication path of the CSI measurement device. Another experiment showed that even when a person wanders around a room, an approximate location can be estimated by using an appropriate combination of CSI measurement devices. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | wireless sensing / channel state information / YOLO |
Paper # | SeMI2022-81 |
Date of Issue | 2023-01-12 (SeMI) |
Conference Information | |
Committee | SeMI |
---|---|
Conference Date | 2023/1/19(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Naruto grand hotel |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Koji Yamamoto(Kyoto Univ.) |
Vice Chair | Kazuya Monden(Hitachi) / Yasunori Owada(NICT) / Shunsuke Saruwatari(Osaka Univ.) |
Secretary | Kazuya Monden(NTT DOCOMO) / Yasunori Owada(Tokyo Univ. of Agri. and Tech.) / Shunsuke Saruwatari(Osaka Univ.) |
Assistant | Yuki Matsuda(NAIST) / Akihito Taya(Aoyama Gakuin Univ.) / Takeshi Hirai(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Sensor Network and Mobile Intelligence |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Short Paper] An experimental study on the transition of camera-based human localization to CSI sensing |
Sub Title (in English) | |
Keyword(1) | wireless sensing |
Keyword(2) | channel state information |
Keyword(3) | YOLO |
1st Author's Name | Kanare Kodera |
1st Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
2nd Author's Name | Shoki Ohta |
2nd Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
3rd Author's Name | Takayuki Nishio |
3rd Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
Date | 2023-01-19 |
Paper # | SeMI2022-81 |
Volume (vol) | vol.122 |
Number (no) | SeMI-341 |
Page | pp.pp.43-48(SeMI), |
#Pages | 6 |
Date of Issue | 2023-01-12 (SeMI) |