Moving object recognition with cooperative training of various image sensing data
| Project/Area Number |
15K21231
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perceptual information processing
Measurement engineering
|
|---|
| Research Institution | Nagasaki University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 画像認識 / 画像解析 |
|---|
| Outline of Final Research Achievements |
The purpose of this research is to develop an accurate image recognition system for outer scene with various surveillance image sensors. The image recognition in the outer scene becomes a difficult task since background objects and the lighting conditions heavily affect to recognition results. In this research, to address the problem of computation burden of image analysis of various images sensors, a changing rate from the past of each region is defined and it is used to extract the regions of interest. The changing rate of each region is calculated based on the subspace method. The selected changing regions are sent to the image recognition part to analyze whether they include some objects of interest. By using the presented method, we can realize the image recognition system which can handle various image sensor’s information of the outer scene.
|
Report
(4 results)
Research Products
(2 results)
