Cloud Coverage Estimation Network for Remote Sensing Images

The main purpose of cloud detection is to estimate cloud coverage and thus determine whether to transmit remote sensing images to earth or execute subsequent tasks based on cloud coverage. Fast and accurate cloud coverage estimation is a necessary preprocessing step on board. Therefore, we propose a new approach for cloud coverage estimation using a regression network to directly predict the coverage. A cloud coverage estimation network, which is termed $\text{C}^{2}\text{E}$ -Net, is proposed in this work. The proposed network consists of three modules, including an encoder for representation feature extraction, a coverage estimation for predicting the cover rate of clouds, and an auxiliary supervision module for improving the performance of the model. To verify the effectiveness of our method, experiments are performed on two open-source datasets (Landset 8 Biome dataset and GaoFen-1 WFV dataset). Our method effectively improves the efficiency of cloud detection by at least doubling, while keeping the estimation error low.

[1]  Chia-Wen Lin,et al.  Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion , 2022, IEEE Transactions on Image Processing.

[2]  Shao Xiang,et al.  Semantic Segmentation for Remote Sensing Images Based on Adaptive Feature Selection Network , 2021, IEEE Geoscience and Remote Sensing Letters.

[3]  Jing Xiao,et al.  Image Inpainting Guided by Coherence Priors of Semantics and Textures , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Chia-Wen Lin,et al.  Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes , 2020, ECCV.

[5]  Jianming Liang,et al.  UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation , 2019, IEEE Transactions on Medical Imaging.

[6]  Rune Hylsberg Jacobsen,et al.  A cloud detection algorithm for satellite imagery based on deep learning , 2019, Remote Sensing of Environment.

[7]  Zhiwei Li,et al.  Deep learning based cloud detection for remote sensing images by the fusion of multi-scale convolutional features , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[8]  Zhen Li,et al.  Cloud Detection in Satellite Images Based on Natural Scene Statistics and Gabor Features , 2019, IEEE Geoscience and Remote Sensing Letters.

[9]  Shenghua Gao,et al.  CE-Net: Context Encoder Network for 2D Medical Image Segmentation , 2019, IEEE Transactions on Medical Imaging.

[10]  Jun Sun,et al.  Cloud and Cloud Shadow Detection Using Multilevel Feature Fused Segmentation Network , 2018, IEEE Geoscience and Remote Sensing Letters.

[11]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[12]  Lei Guo,et al.  When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[13]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[14]  Zhe Zhu,et al.  Cloud detection algorithm comparison and validation for operational Landsat data products , 2017 .

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Pengfei Li,et al.  A cloud image detection method based on SVM vector machine , 2015, Neurocomputing.

[17]  Xiangyun Hu,et al.  Bag-of-Words and Object-Based Classification for Cloud Extraction From Satellite Imagery , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[18]  Roberto Basili,et al.  Techniques based on Support Vector Machines for cloud detection on QuickBird satellite imagery , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[19]  Sylvie Le Hégarat-Mascle,et al.  Use of Markov Random Fields for automatic cloud/shadow detection on high resolution optical images , 2009 .

[20]  A. Lacis,et al.  Calculation of radiative fluxes from the surface to top of atmosphere based on ISCCP and other global data sets: Refinements of the radiative transfer model and the input data , 2004 .