Digitally refocusing an unfocused image
Satellite imagery plays a critical role in various applications, including environmental monitoring, urban planning, and navigation. However, optical distortions in satellite images can affect their accuracy and interpretability. This project focuses on digitally refocusing unfocused satellite image...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
Nanyang Technological University
2023
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/167611 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | Satellite imagery plays a critical role in various applications, including environmental monitoring, urban planning, and navigation. However, optical distortions in satellite images can affect their accuracy and interpretability. This project focuses on digitally refocusing unfocused satellite images of real-life road conditions using machine learning models. Two state-of-the-art models are evaluated, and a deep Wiener deconvolution network is used to deblur the images. Diverse datasets of satellite images are used to train the models, and the results show that the proposed technique can effectively restore the sharpness and details of the images, leading to significant improvements in metrics, such as peak signal-to-noise ratio. The strengths and weaknesses of the models are analyzed comprehensively, highlighting the challenges and potential improvements. The study concludes that machine learning models have the potential to enhance the quality and reliability of satellite imagery, opening up new opportunities for image-based applications. Future research directions are suggested to further enhance the effectiveness of the proposed technique. |
|---|