| Presentation | 2023-06-17 Improved Visual Intentions Estimation Model Using Depth Information and Object Detection Sho Higa, Masakiyo Okuhama, Koji Yamada, Shihoko Kamisato, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this study, we propose an improved visual intention estimation model based on object detection to distinguish eye and head movements during looking away, paying attention and checking the environment. The proposed model consists of a 1DCNN-LSTM and takes as input "looking object" and "distance to object" in addition to time series data of eye and head movements. Comparison experiments on estimation accuracy showed that the F-measure of the proposed model tended to be higher than that of the traditional model, suggesting that feature vectors such as "looking object" and "distance to object" contribute to the improvement of estimation accuracy. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | visual intentions / intention recognition / electric wheelchair / one-dimensional convolutional neural network / long short-term memory |
| Paper # | WIT2023-17 |
| Date of Issue | 2023-06-09 (WIT) |
| Conference Information | |
| Committee | WIT |
|---|---|
| Conference Date | 2023/6/16(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Okinawa Industry Support Center |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinji Sakou(Nagoya Inst. of Tech.) |
| Vice Chair | Tomohiro Amemiya(Univ. of Tokyo) |
| Secretary | Tomohiro Amemiya(Saitama Industrial Tech. Center) |
| Assistant | Minako Hosono(AIST) / Aki Sugano(Univ. of Toyama) / Tomoyasu Komori(NHK) |
| Paper Information | |
| Registration To | Technical Committee on Well-being Information Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Improved Visual Intentions Estimation Model Using Depth Information and Object Detection |
| Sub Title (in English) | |
| Keyword(1) | visual intentions |
| Keyword(2) | intention recognition |
| Keyword(3) | electric wheelchair |
| Keyword(4) | one-dimensional convolutional neural network |
| Keyword(5) | long short-term memory |
| 1st Author's Name | Sho Higa |
| 1st Author's Affiliation | University of the Ryukyus(Ryukyu Univ.) |
| 2nd Author's Name | Masakiyo Okuhama |
| 2nd Author's Affiliation | University of the Ryukyus(Ryukyu Univ.) |
| 3rd Author's Name | Koji Yamada |
| 3rd Author's Affiliation | University of the Ryukyus(Ryukyu Univ.) |
| 4th Author's Name | Shihoko Kamisato |
| 4th Author's Affiliation | National Institute of Technology, Okinawa College(NIT,Okinawa College) |
| Date | 2023-06-17 |
| Paper # | WIT2023-17 |
| Volume (vol) | vol.123 |
| Number (no) | WIT-81 |
| Page | pp.pp.76-77(WIT), |
| #Pages | 2 |
| Date of Issue | 2023-06-09 (WIT) |