No abstract

No abstract

No abstract

No abstract

Remote sensing images (RSIs) captured in haze weather will suffer from serious quality degradation with color distortion and contrast reduction, which creates numerous challenges for the utilization of RSIs. To address these issues, this paper proposes a novel haze removal algorithm, named HALP, for visible RSIs based on a heterogeneous atmospheric light prior and side window filter. HALP is comprised of two key components. Firstly, given the large imaging space of RSIs, the atmospheric light is treated as a globally non-uniform distribution instead of a global constant. Therefore, a simple and effective method for non-uniform atmospheric light estimation is presented, which utilizes the brightest pixel color in each local image patch as the atmospheric light of the local region. Secondly, a side window filter-based transmission estimation algorithm is proposed, which can effectively suppress the block effect in the transmission map caused by the large window of the minimum filter used in the dark channel algorithm. Experiments on both real-world and synthetic remote sensing haze images demonstrate the effectiveness of HALP. In terms of no-reference and full-reference image quality assessments, HALP yields excellent results, outperforming existing state-of-the-art algorithms, including physics-based and neural network-based methods. The visual comparison of dehazed results also shows that HALP can restore degraded RSIs with uneven haze, producing clear images with rich details and natural colors.INDEX TERMS Dehazing, remote sensing image, heterogeneous atmospheric light, image restoration, dark channel.

No abstract

Images captured in hazy weather often suffer from color distortion and texture blur due to turbid media suspended in the atmosphere. In this paper, we propose a Feature Attention Parallel Aggregation Network (FAPANet) to restore a clear image directly from the corresponding hazy input. It adopts the encoder-decoder structure while incorporating residual learning and attention mechanism. FAPANet consists of two key modules: a novel feature attention aggregation module (FAAM) and an adaptive feature fusion module (AFFM). FAAM recalibrates features by integrating channel attention and pixel attention in parallel to stimulate useful information and suppress redundant features. The shallow and deep layers of neural networks tend to characterize the low-level and high-level semantic features of images, respectively, so we introduce AFFM to fuse these two features adaptively. Meanwhile, a joint loss function, composed of L1 loss, perceptual loss, and structural similarity (SSIM) loss, is employed in the training stage for better results with more vivid colors and richer details. Comprehensive experiments on both synthetic and real-world images demonstrate the impressive performance of the proposed approach.

Mastering accurate spatial planting and distribution status of the crops is significantly important for the nation to guide the agricultural production and formulate agricultural policies from a macro perspective. In this paper, the Landsat-8 OLI satellite images were taken as the data sources. And as for the nine crop types within the study area, such as the wheat, rice, and other crops, three classification methods of the random forest classification (RFC), the support vector machine (SVM), and the maximum likelihood classification (MLC) were applied in extracting the planting area of winter wheat in Wushi County of Xinjiang Uygur Autonomous Region. It can be seen from the results that, general classification accuracy of MLC, SVM, and RFC are respectively 80.58%, 87.95%, and 95.96%, while their Kappa coefficients are respectively 0.61, 0.76, and 0.86. The RFC method shows higher classification accuracy that those of MLC and SVM methods. The principal component analysis (PCA) was carried out on the original 7-band image to extract the first 4 principal components and calculate the normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), wide dynamic range vegetation index (WDRVI), and normalized difference water index (NDWI). Meanwhile, the 6 additional auxiliary feature bands were superimposed on the original 7-band images to carry out reclassification, through which, the general accuracy of MLC increased by 3 percent while its Kappa coefficient increased by 0.06; the SVM general accuracy increased by 3.02 percent while its Kappa coefficient increased by 0.13; and the general accuracy of the RFC increased by 0.85 percent while its Kappa coefficient increased by 0.02. This indicates that, the adding of auxiliary information can improve the crop classification and identification ability and accuracy. Based on the comprehensive evaluation, the classification method of random forest is proved to have better performance in winter wheat identification.