| Budget Amount *help |
¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2012: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2011: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Research Abstract |
In this study, we assume groups of local image features obtained from the scene as the markers for rendering of virtual objects in augmented reality systems. For this purpose, we proposed a CG simulation method to evaluate existing various local feature descriptors proposed by many researchers so far in the situations including occlusions.
In addition, we applied visual-SLAM approach, which is widely used in the robotics area, to estimate the position and the orientation of the device by combining its accelerometer data and image feature with considering uncertainty of these observations. Furthermore, we proposed a method to estimate the position of light sources from casting shadows of a "landmark object" in the scene. With these results, we have implemented a prototype AR-system onto Android tablet.
|
