Discriminative Feature Learning Constrained Unsupervised Network for Cloud Detection in Remote Sensing Imagery

Abstract

Cloud detection is a significant preprocessing step for increasing the exploitability of remote sensing imagery that faces various levels of difficulty due to the complexity of underlying surfaces, insufficient training data, and redundant information in high-dimensional data. To solve these problems, we propose an unsupervised network for cloud detection (UNCD) on multispectral (MS) and hyperspectral (HS) remote sensing images. The UNCD method enforces discriminative feature learning to obtain the residual error between the original input and the background in deep latent space, which is based on the observation that clouds are sparse and modeled as sparse outliers in remote sensing imagery. The UNCD enforces discriminative feature learning to obtain the residual error between the original input and the background in deep latent space, which is based on the observation that clouds are sparse and modeled as sparse outliers in remote sensing imagery. First, a compact representation of the original imagery is obtained by a latent adversarial learning constrained encoder. Meanwhile, the majority class with sufficient samples (i.e., background pixels) is more accurately reconstructed than the clouds with limited samples by the decoder. An image discriminator is used to prevent the generalization of out-of-class features caused by latent adversarial learning. To further highlight the background information in the deep latent space, a multivariate Gaussian distribution is introduced. In particular, the residual error with clouds highlighted and background samples suppressed is applied in the cloud detection in deep latent space. To evaluate the performance of the proposed UNCD method, experiments were conducted on both MS and HS datasets that were captured by various sensors over various scenes, and the results demonstrate its state-of-the-art performance. The sensors that captured the datasets include Landsat 8, GaoFen-1 (GF-1), and GaoFen-5 (GF-5). Landsat 8 was launched at Vandenberg Air Force Base in California on 11 February 2013, in a mission that was initially known as the Landsat Data Continuity Mission (LDCM). China launched the GF-1 satellite. The GF-5 satellite captures hyperspectral observations in the Chinese Key Projects of High-Resolution Earth Observation System. The overall accuracy (OA) values for Images I and II from the Landsat 8 dataset were 0.9526 and 0.9536, respectively, and the OA values for Images III and IV from the GF-1 wide field of view (WFV) dataset were 0.9957 and 0.9934, respectively. Hence, the proposed method outperformed the other considered methods.

ShuffleCloudNet: A Lightweight Composite Neural Network-Based Method for Cloud Computation in Remote-Sensing Images

“…The rapid development of deep learning in recent years has led to the application of methods involving deep convolutional neural networks to cloud detection, which has facilitated the rapid development of cloud detection and cloud-amount computing due to its very powerful feature representation and scene application capabilities [10][11][12][13][14][15][16][17][18]. The convolutional neural network-based approach can achieve automatic feature acquisition and automatic classification by establishing a nonlinear mapping from input to output.…”

Validation of atmospheric correction approaches for Sentinel-2 under partly-cloudy conditions in an African agricultural landscape

“…Their results, using GF-1 images, showed a mean accuracy of >90% and a reduction in processing time by >80%. Recently, the new approaches for cloud removal, based on deep learning algorithms, have been proposed for various optical sensors [12,13]. While these methods are useful for removing clouds and cloud shadows, the radiometric integrity of the cloud-free pixels in partly cloudy images rarely studied.…”