| Presentation | 2012/1/12 Human Pose Estimation in Complex Scenes Using Region Features SHINSUKE OKANO, NORIMICHI UKITA, NORIHIRO HAGITA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose a method for estimating a human body pose from a single image with cluttering background. This paper focus on how to extract useful image features robustly against the backgound clutter. While existing gradient-based features should contain nuisance parts such as texture patterns of the face and clothing as well as the background clutter, our proposed features might represent only the boundary lines of the body parts by binary segmentation of the parts and the background. The binary segmentation is achieved in every possible region of the body parts. In each segmentation, seed pixels of body-parts and background pixels are located depending on the type of the target body part. Comparative expermients with a public dataset demonstrates the effectiveness of our features.We propose a method for estimating a human body pose from a single image with cluttering background. This paper focus on how to extract useful image features robustly against the backgound clutter. While existing gradient-based features should contain nuisance parts such as texture patterns of the face and clothing as well as the background clutter, our proposed features might represent only the boundary lines of the body parts by binary segmentation of the parts and the background. The binary segmentation is achieved in every possible region of the body parts. In each segmentation, seed pixels of body-parts and background pixels are located depending on the type of the target body part. Comparative expermients with a public dataset demonstrates the effectiveness of our features. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | |
| Paper # | Vol.2012-CVIM-180 No.9 |
| Date of Issue |
| Conference Information | |
| Committee | MVE |
|---|---|
| Conference Date | 2012/1/12(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) | Human Pose Estimation in Complex Scenes Using Region Features |
| Sub Title (in English) | |
| Keyword(1) | |
| 1st Author's Name | SHINSUKE OKANO |
| 1st Author's Affiliation | Nara Institute of Science and Tedmology(NAIST)() |
| 2nd Author's Name | NORIMICHI UKITA |
| 2nd Author's Affiliation | Nara Institute of Science and Tedmology(NAIST) |
| 3rd Author's Name | NORIHIRO HAGITA |
| 3rd Author's Affiliation | Nara Institute of Science and Tedmology(NAIST):Advanced Telecommunications Research Institute International(ATR) |
| Date | 2012/1/12 |
| Paper # | Vol.2012-CVIM-180 No.9 |
| Volume (vol) | vol.111 |
| Number (no) | 380 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |