A study of object extraction and recognition for partially hidden objects
Project/Area Number |
26330201
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Perceptual information processing
|
Research Institution | University of Hyogo |
Principal Investigator |
|
Research Collaborator |
TAJIKA Kazuyoshi 株式会社ブレイン
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Project Status |
Completed (Fiscal Year 2016)
|
Budget Amount *help |
¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2014: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
|
Keywords | 物体認識 / RGB-Dセンサ / 視点変換 / 凸包補間形状特徴 / 三次元データ合成 / 画像認識 / 物体識別 / 距離画像センサ / 画像領域分割 |
Outline of Final Research Achievements |
To improve recognition accuracy of clouded objects, we employ RGB-D sensor to achieve 3D shape data. For an object which changes its posture by getting on other objects, we apply view point transform to normalize its appearance to improve recognition accuracy. For an object which partially concealed by other objects, we extract shape features for its convex envelope to improve recognition accuracy. We also discuss optimum positioning of camera set to achieve best recognition accuracy.
|
Report
(4 results)
Research Products
(6 results)