2013 Fiscal Year Final Research Report
Gait identification from invisible shadows
| Project/Area Number |
23500216
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
IWASHITA Yumi 九州大学, システム情報科学研究科(研究院, 助教 (70467877)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KURAZUME Ryo 九州大学, 大学院・システム情報科学研究院, 教授 (70272672)
MOROOKA Ken'ichi 九州大学, 大学院・システム情報科学研究院, 准教授 (80323806)
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Keywords | 個人認証 / 歩容 / 影生体情報 / 赤外線 |
|---|
| Research Abstract |
Gait is a powerful remote biometric, offering the advantages of identification from a distance, and of being unobtrusive. We proposed a person identification technique that uses information from person's shadow. In the proposed system, we obtain the advantages of multiple viewpoints with a single camera and additional light sources. More specific, we install multiple infrared lights, which have advantages as undetected sensing, to project shadows of a subject on the ground and a camera in the ceiling inside of a building. Shadow areas, which are projections of one's body on the ground by multiple lights, can be considered as body areas captured from different viewpoints; thus, the proposed system is able to capture multiple projections of the body from a single camera. In addition, we extended the proposed system to improve its performance, by introducing a voting-based method. We showed that the proposed system outperformed an existing method with a database consisting of 54 people.
|
