2003 Fiscal Year Final Research Report Summary
Recovery of body postures from a monocular image wequence based on probabilistic model learning
| Project/Area Number |
14580427
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Hiroshima City University |
|---|
Principal Investigator |
HAYASHI Akira Hiroshima City University, Faculty of Information Sciences, Professor, 情報科学部, 教授 (60240909)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
OKADA Masami Tokyo Metropolitan University, Faculty of Science, Professor, 理学研究科, 教授 (00152314)
KANBARA Toshihiko Hiroshima City University, Faculty of Information Sciences, Research Associate, 助手 (60285426)
SUEMATSU Nobuo Hiroshima City University, Faculty of Information Sciences, Research Associate, 助教授 (70264942)
|
|---|
| Project Period (FY) |
2002 – 2003
|
| Keywords | pose estimation / monocular image / state space model / sequential Mote Carlo / 逐次モンテカルロ法 / モーションキャプチャ |
|---|
| Research Abstract |
In the fields of visual surveillance, welfare robotics, and human interface, it is important that a computer can recognize the posture/motion of people. In this research, we try to estimate human postures from monocular image sequences.
We propose the cyclic motion model which is a state space model to represent motions. In the model, the state of a system is represented by the phase of a motion, assuming that the motion is cyclic. The state (i.e. the phase) is estimated from a monocular image sequence using the sequential Monte Carlo method. Then, the posture is computed from the state. The cyclic motion model is learned from motion capture data. In addition, we extend the cyclic motion model to allow for camera viewpoint changes.
Experiments show the validity of the proposed technique.
|
Research Products
(8 results)
