| Project/Area Number |
26350454
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Social systems engineering/Safety system
|
|---|
| Research Institution | University of the Ryukyus |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2014: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | 防犯カメラ / 安全工学 / 機械学習 / 画像処理 / 人工知能 / 社会システム / 挙動解析 / ひったくり / 社会安全 / 行動解析 / 数理モデル / 犯罪行動モデル / 社会安全システム / 画像情報処理 / 自動検知 |
|---|
| Outline of Final Research Achievements |
In this research, we focused on an intelligent security camera system for automated detection of snatching incident. Also, BSAM(Basic Snatching Action Model) is presented to give a definition of the snatching incident. The localization of moving objects in a video stream and human behavior estimation are key techniques for the developed system. Some motion characteristics are determined from video streams, and using machine learning systems, the system automatically classifies the situation of the video streams into criminal or non-criminal scenes. After constructing the classifier system, we use test sequences that are continuous video streams of human behavior consisting of several actions in succession. We consider four types of scenarios for the experiments of the snatching incident. The experimental results show that the system can effectively detect criminal scenes at high accuracy. These results are published as some peer-reviewed papers.
|
