Post-disaster Recovery Monitoring based on Multi-Source Remote Sensing Imagery and Deep Learning
| Project/Area Number |
21K14261
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 22050:Civil engineering plan and transportation engineering-related
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
郭 直霊 東京大学, 空間情報科学研究センター, 客員研究員 (40897716)
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Project Status |
Completed (Fiscal Year 2023)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2023: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2022: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2021: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | Post-disaster Monitoring / Deep Learning / Remote Sensing / Computer Vision / Change Detection |
|---|
| Outline of Research at the Start |
This research addresses the challenge of achieving high performance recovery monitoring and related tasks based on inexact and inadequate training dataset. The weak-supervised learning, multi-task learning, transfer learning is proposed.
This research sets up an architecture which makes connecting between the research fields of urban mapping, change detection, and recovery monitoring.
Based on this research, more interdisciplinary datasets and methods are expected to for post-disaster recovery monitoring optimization to promote the efficiency and accuracy.
|
| Outline of Annual Research Achievements |
For a large-scale and long-lasting post-disaster recovery monitoring, problems caused by multi-source remote sensing imagery such as the difference in land features, resolution, and spectrum, have been solved by transfer learning methods. Thus, a small amount of training datasets have been obtained for model transfer. After that, multi-temporal UAV aerial imagery has been put into the transferred multi-task urban mapping model for multi-temporal land feature extraction. Finally, the generated land features including semantic, object, and DEM have been utilized to achieve high-performance recovery monitoring via the transferred change detection model. In this year, the results of the aforementioned steps have been integrated, and the experimental post-disaster recovery monitoring has been deployed in cooperation with communication and companies. With the analysis of the experimental results, the rest of the time in FY2023 has been devoted to the conclusions of the theories, methods, and findings derived from this research. Additionally, the monitoring methods have been open for the society with practical applications, publications, and web service, which will lead to the future evolvement and application of post-disaster recovery monitoring in broader usages.
|
Report
(3 results)
Research Products
(11 results)
