| Project/Area Number |
16K18162
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Civil engineering project/Traffic engineering
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
XU YONGWEI 東京大学, 地球観測データ統融合連携研究機構, 特任研究員 (10726897)
|
|---|
| Project Period (FY) |
2016-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2017: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2016: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | 深層学習 / スパースモデリング / 人の流れ / 異常検出 / 機械学習 |
|---|
| Outline of Final Research Achievements |
In this research, based on the people tracking data, by using the Sparse Coding method, we designed the real-time mapping system which can detect abnormality and people flow density and flow trend.
In the past research, the approach centered on a technology based on individually detecting and tracking each person. This research differs from the past that it does not detect or track individual persons, treats the flow of people as "group" rather than individual gathering, divides the flow map with a mesh, and measures the density and fluctuation of the flow. As a result, we analysis and predict the people flow trend from the information of density map, and the method also able to detect people flow abnormality.
|
