Research for accelerating criminal investigation by improving security camera image and innovating identification technology
Project/Area Number |
25280088
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Partial Multi-year Fund |
Section | 一般 |
Research Field |
Intelligent informatics
|
Research Institution | Ritsumeikan University |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
泉 知論 立命館大学, 理工学部, 准教授 (30303887)
福水 洋平 立命館大学, 理工学部, 准教授 (60467008)
|
Project Period (FY) |
2013-04-01 – 2017-03-31
|
Project Status |
Completed (Fiscal Year 2016)
|
Budget Amount *help |
¥15,470,000 (Direct Cost: ¥11,900,000、Indirect Cost: ¥3,570,000)
Fiscal Year 2015: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2014: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2013: ¥5,590,000 (Direct Cost: ¥4,300,000、Indirect Cost: ¥1,290,000)
|
Keywords | 画像鑑定 / 画像鮮明化 / 3Dスーパーインポーズ / 歩容認証 / 劣化数字認識 / 3Dスーパーインポーズ / 歩容の異同識別 / 人物間接モデル / アバター生成 / 顔と身体の異同識別 / ナンバープレート読み取り / 犯罪捜査 / 防犯カメラ / 3Dインポーズ / 画像超解像 / 人物異同識別 / 歩容識別 / ビッグデータ / 絶対類似性判断 / 超解像 / 3Dインポーズ / 画像処理Viewer / 人物検出 / 人物姿勢推定 |
Outline of Final Research Achievements |
We gave four achievements. The first was to improve the face image with strong degradation greatly and to improve the accuracy of face identification. The second is to make it possible to handle similarity stochastically in face identification by 3D superimpose technology. Thirdly, we have made it possible to handle similarity stochastically in gait identification by walking identification. Fourth is improving recognition accuracy of license plate certification.
|
Report
(5 results)
Research Products
(13 results)