| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2015: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Outline of Final Research Achievements |
The purpose of this study is to develop an information platform to support the maintenance of social infrastructure, and to contribute to the efficiency and rationalization of maintenance.
Visual inspection is very important for maintenance of infrastructure. Therefore, in order to support visual inspection, we applied image recognition using deep learning to images acquired by digital cameras and developed a system that automatically assesses classifications related to ranking by detecting deformations. Furthermore, we have developed a system that not only ranks damages but also uses Semantic Segmentation by deep learning to extract damage areas in pixel units for each damage. As a result, it became possible to quantitatively judge whether the damaged area has expanded by periodic inspection every five years, and the accuracy of deterioration prediction was improved.
|
