2023 Fiscal Year Annual Research Report
Post-disaster Recovery Monitoring based on Multi-Source Remote Sensing Imagery and Deep Learning
| Project/Area Number |
21K14261
|
|---|
| 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
|
| Keywords | Post-disaster Monitoring / Deep Learning / Remote Sensing / Computer Vision |
|---|
| 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.
|
