Loading...
Please wait, while we are loading the content...
Similar Documents
Multi-level Cloud Detection in Remote Sensing Images Based on Deep Learning
| Content Provider | Semantic Scholar |
|---|---|
| Author | Xie, Fengying Shi, Mengyun Shi, Zhenwei Yin, Jihao Zhao, Danpei |
| Copyright Year | 2017 |
| Abstract | Cloud detection is one of important tasks for remote sensing image processing. In this paper, a novel multi-level cloud detection method based on deep learning is proposed for remote sensing images. Firstly, the simple linear iterative clustering (SLIC) method is improved to segment the image into good quality superpixels. Then a deep Convolutional Neural Network (CNN) with two branches is designed to extract the multi-scale features from each superpixel and predict the superpixel as one of three classes including thick cloud, thin cloud and noncloud. Finally, the predictions of all the superpixels in the image yield the cloud detection result. In the proposed cloud detection framework, the improved SLIC method can obtain accurate cloud boundaries by optimizing initial cluster centers, designing dynamic distance measure and expanding search space. Moreover, different from traditional cloud detection methods which cannot achieve multi-level detection of cloud, the designed deep CNN model can not only detect cloud but also distinguish thin cloud from thick cloud. Experimental results indicate that the proposed method can detect cloud with higher accuracy and robustness than compared methods. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://levir.buaa.edu.cn/publications/Multi-level_Cloud_Detection_in_Remote_Sensing.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
