| Proj No. | A3225-251 |
| Title | Deep Generative Model for Remote Sensing |
| Summary | Remote sensing is an important approach for applications such as earth monitoring, navigation, disaster and hazard control. We used to sense, process and analyze the remote sensing data manually, which is inefficient especially when dealing with big data applications. With the advance of artificial intelligence and computer vision, tasks such as target detection and image segmentation can be now be done automatically via smart algorithms. Conventional computer vision algorithms focused on analyzing natural images with visible lights. However, in remote sensing, there are many other important computational imaging systems such as synthetic aperture radar imaging, multispectral image fusion, as well as infra-red imaging. They all enjoy unique advantages and properties, whereas the training data is expensive to be obtained. In this project, we aim to develop an image synthesis algorithm based on the recent Generative Adversarial Network (GAN). The goal is to transfer large-scale optical RGB images to the desired imaging modalities, e.g., SAR, in remote sensing. Such algorithms will be extremely important for training AI networks over remote sensing data. Interested students can contact me (bihan.wen@ntu.edu.sg) and attach their CV/resume/degree audit. |
| Supervisor | A/P Wen Bihan (Loc:S2 > S2 B2B > S2 B2B 54, Ext: +65 67904708) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Satellite Research Centre (Loc: S2.2-B3-06) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |