Abstract
Missing data reconstruction for remote sensing images, such as dead-pixel recovery and cloud removal, is important for remote sensing data applications. Missing information reconstruction is well known as being an ill-posed inverse problem. In this paper, a weighted low-rank tensor regularization model is proposed to handle the problem. The proposed model fully utilizes the correlations in the spatial, spectral, and temporal components of the remote sensing images to adaptively deal with the varied missing data problems, including the Aqua Moderate Resolution Imaging Spectroradiometer (MODIS) band 6 dead line problem, the Landsat scan-line corrector failure (SLC-off) problem, and cloud contamination. A double-weighted treatment is developed to balance the contributions from the different dimensions and preserve the different structures and textures in remote sensing images. The experiments undertaken confirmed the good performance of the proposed method, and the reconstruction results of the proposed method, in both visual effect and quantitative evaluation, were superior to those of the other methods.
Highlights
Malfunction of remote sensing sensors and cloud contamination often cause missing data problems for remote sensing images
Hybrid methods based on tensor recovery have been proposed [21], [22], but the high correlation in remote sensing data is still not fully utilized, and the detail and texture preservation ability is still limited. To remedy these limitations, we propose a spatial-spectral-temporal method termed the doubleweighted low-rank tensor (DWLRT) model to reconstruct missing data in remote sensing images
EXPERIMENTAL RESULTS AND ANALYSIS Two simulated data experiments and three real data experiments were implemented to test the performance of the proposed DWLRT method
Summary
Malfunction of remote sensing sensors and cloud contamination often cause missing data problems for remote sensing images. Typical cases are the dead pixels in the Aqua Moderate Resolution Imaging Spectroradiometer (MODIS) band 6 (Fig. 1(a)) and the Landsat Enhanced Thematic Mapper Plus (ETM+) scan-line corrector (SLC)-off problem (Fig. 1(b)). Cloud contamination is generally present in remote sensing data (Fig. 1(c)). Missing data reconstruction remains an important task for remote sensing data applications. Many different approaches have been developed in recent decades to handle this problem, and a comprehensive technical review can be found in [1]. The complementary information from the different domains allows us to partition the current methods into spatial-based, spectral-based, and temporal-based methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
