Abstract
In remote sensing images, the presence of thick cloud accompanying shadow can affect the quality of subsequent processing and limit the scenarios of application. Hence, to make good use of such images, it is indispensable to remove the thick cloud and cloud shadow as well as recover the cloud-contaminated pixels. Generally, the thick cloud and cloud shadow element are not only sparse but also smooth along the spatial horizontal and vertical direction, while the clean element is smooth along the temporal direction. Guided by the above insight, a novel thick cloud removal method for remote sensing images based on temporal smoothness and sparsity regularized tensor optimization (TSSTO) is proposed in this paper. Firstly, the sparsity norm is utilized to boost the sparsity of the cloud and cloud shadow element, and unidirectional total variation (UTV) regularizers are applied to ensure the smoothness in different directions. Then, through thresholding, the cloud mask and the cloud shadow mask can be acquired and used to guide the substitution. Finally, the reference image is selected to reconstruct details of the repairing area. A series of experiments are conducted both on simulated and real cloud-contaminated images from different sensors and with different resolutions, and the results demonstrate the potential of the proposed TSSTO method for removing cloud and cloud shadow from both qualitative and quantitative viewpoints.
Highlights
Remote sensing images have been widely used in many research and application fields, such as classification [1,2], object detection [3], and urban geographical mapping [4]
Different from the methods as mentioned above, this paper proposes a novel tensor optimization model based on temporal smoothness and sparse representation (TSSTO) for thick cloud and cloud shadow removal in remote sensing images
Group sparsity is used to enhance the sparsity of the cloud/shadow, and two unidirectional total variation regularizers along the horizontal and vertical direction are designed to deal with the large cloud/shadow area
Summary
Remote sensing images have been widely used in many research and application fields, such as classification [1,2], object detection [3], and urban geographical mapping [4]. The spatial information-based methods are dedicated to recovering the cloud-contaminated pixels by making full use of the information from the cloud-free area in the image to be repaired. The temporal information-based methods can obtain satisfactory results, as long as the spectral difference and the land cover change are not too discrepant between the target image and reference image. Different from the methods as mentioned above, this paper proposes a novel tensor optimization model based on temporal smoothness and sparse representation (TSSTO) for thick cloud and cloud shadow removal in remote sensing images. Group sparsity is used to enhance the sparsity of the cloud/shadow, and two unidirectional total variation regularizers along the horizontal and vertical direction are designed to deal with the large cloud/shadow area This scheme enables TSSTO better to remove both the large and small cloud-contaminated area.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
