2016 Fiscal Year Final Research Report
Spatiotemporal data mining for group behavior analysis in indoors
| Project/Area Number |
25330186
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | Chiba University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2013-04-01 – 2017-03-31
|
| Keywords | データ同化 / 人物追跡 / 行動認識 |
|---|
| Outline of Final Research Achievements |
We developed a vision-based method for analyzing people group behavior in indoors. Such methods are widely required due to the increased demands in several applications such as security. To analyze complex people group behavior, we introduced a data assimilation framework, which is used to estimate and update the parameters and state of numerical simulation models, and applied it to people tracking. In addition, we developed associated vision-based technologies such as pedestrian detection, position estimation, and activity recognition.
|
| Free Research Field |
コンピュータビジョン
|
