2015 Fiscal Year Final Research Report
Game Theoretic Learning Approach to Cooperative Active Sensing for Visual Sensor Networks
| Project/Area Number |
25420430
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Control engineering/System engineering
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Keywords | 制御理論 / ゲーム理論 / 協調制御 / ビジュアルセンサネットワーク / 能動センシング |
|---|
| Outline of Final Research Achievements |
In this project, we have presented distributed active sensing methods for a visual sensor network, a networked multi-camera system, so as to maximize the acquired information on environment. We first have developed two different active sensing methodologies based on game theoretic learning theory, which do never require prior knowledge on uncertain environment. We then have presented another approach using distributed optimization on matrix manifolds in order to accelerate adaptability to environmental changes. In addition, a novel distributed target motion prediction algorithm has been proposed in the project. Moreover, we have built a testbed of the visual sensor network system and then have demonstrated all of the above algorithms. Also, a novel simulator of the sensor network system has been developed using a 3D animation software, called blender.
|
| Free Research Field |
制御工学
|
