| Presentation | 2013-03-11 Fundamental Study of Judging Sleeper's Turnovers from Depth Image Sequences by Support Vector Machine Yuta Minezaki, Jun Ohya, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, care of aged people's turnovers is heavy burdens for helpers; in particular, automatic judgment of turnovers is desired. This paper proposes a method that can judge whether aged people being cared turned over by utilizing a depth image sequence acquired by Kinect sensor that observes the aged people in beds. Specifically, image features are extracted from aged people's bodies in the depth image sequences. and are used for classification by Support Vector Machine. As the image features, this paper uses time series data of "xyz differences between left and right shoulders and between the left and right edges of the waist". and "average depth in each block obtained by partitioning the bed area into w by h blocks" for exploring classification accuracies. Experimental results show that the former and latter features achieve 99.5% and 89.5% classification accuracies, respectively. The fonner gives a better accuracy, but its applicability is limited. while the latter can be applied for more general cases. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Depth image / Support Vector Machine / human body posture estimation / image feature / detection of turnovers / care |
| Paper # | IMQ2012-53,IE2012-157,MVE2012-114,WIT2012-63 |
| Date of Issue |
| Conference Information | |
| Committee | MVE |
|---|---|
| Conference Date | 2013/3/4(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Media Experience and Virtual Environment (MVE) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Fundamental Study of Judging Sleeper's Turnovers from Depth Image Sequences by Support Vector Machine |
| Sub Title (in English) | |
| Keyword(1) | Depth image |
| Keyword(2) | Support Vector Machine |
| Keyword(3) | human body posture estimation |
| Keyword(4) | image feature |
| Keyword(5) | detection of turnovers |
| Keyword(6) | care |
| 1st Author's Name | Yuta Minezaki |
| 1st Author's Affiliation | Graduate School of Global Inatformion and Telecommunication Studies, Waseda University() |
| 2nd Author's Name | Jun Ohya |
| 2nd Author's Affiliation | Graduate School of Global Inatformion and Telecommunication Studies, Waseda University |
| Date | 2013-03-11 |
| Paper # | IMQ2012-53,IE2012-157,MVE2012-114,WIT2012-63 |
| Volume (vol) | vol.112 |
| Number (no) | 474 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |