A method for detecting and removing thick clouds from coarse-to-fine time-series remote sensing images

Abstract

The invention discloses a thick cloud detection and removal method of time series remote sensing image from coarse to fine. Firstly, the image is pre-processed, including super-pixel segmentation andtransformation of the temporal image to form a matrix. The low rank theory and structural sparseness theory are used to model the background (ideal cloudless surface information) and the foreground (cloud and its shadow) respectively, and the time-series images are separated into the foreground and the background by using the robust principal component analysis framework and introducing affine transformation model, and the cloud and cloud shadow regions at super pixel level are obtained. Then, different scaling factors are set for cloud and non-cloud regions, and the original robust principalcomponent analysis is used to decompose them to remove thick clouds from remote sensing images. The invention greatly improves the precision and efficiency of removing thick clouds from remote sensingimages according to unregistered multi-temporal remote sensing image sequences, and can generate high-precision clouds and cloud shadow detection products, and has extremely high multi-temporal remote sensing image research and application value.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and relates to a coarse-to-fine time-series remote sensing image thick cloud detection and removal method. Background technique [0002] Affected by the imaging mechanism of optical sensors, remote sensing images inevitably have cloud occlusion, which seriously affects the image quality. Thick cloud occlusion makes the surface information completely missing, and the accompanying cloud shadow also seriously changes the spectral information, destroys the overall consistency of remote sensing images, and seriously hinders the classification and identification of ground features. Therefore, it is of great significance to remove cloud and cloud shadow pollution in remote sensing images and restore the corresponding surface information. [0003] Traditional cloud removal methods for remote sensing images usually repair cloud occlusion information for a single image or two image...

AI Technical Summary

Problems solved by technology

However, the repair result of the current sparse representation method has fuzzy effect, and the dictionary learning time cost is very high; the compressed sensing method is sensitive to the size of the cloud area and the types of features covered by the cloud area; deep learning is limited by the type and number of training samples

All methods based on cloud-free reference images assume that the target image is strictly registered with the reference image (i.e., pixel-level registration), which leads to limited practicality of such methods

The amount of remote sensing image data is huge, and there are sufficient multi-phase coverage images at the same location. There is no public research and technology for high-precision and high-efficiency batch image cloud removal using multi-temporal image sequences.

Images