High-resolution remote sensing satellites have revolutionized remote sensing research, yet accurately segmenting specific targets from complex satellite imagery remains challenging. While the Segment Anything Model (SAM) has emerged as a promising universal segmentation model, its direct application to remote sensing imagery yields suboptimal results. To address these limitations, we propose RSAM-Seg, a novel deep learning model adapted from SAM specifically designed for remote sensing applications. Our model incorporates two key components: Adapter-Scale and Adapter-Feature modules. The Adapter-Scale modules, integrated within Vision Transformer (ViT) blocks, enhance model adaptability through learnable transformations, while the Adapter-Feature modules, positioned between ViT blocks, generate image-informed prompts by incorporating task-specific information. Extensive experiments across four binary and two multi-class segmentation scenarios demonstrate the superior performance of RSAM-Seg, achieving an $F1$ score of 0.815 in cloud detection, 0.834 in building segmentation, and 0.755 in road extraction, consistently outperforming established architectures like U-Net, DeepLabV3+, and Segformer. Moreover, RSAM-Seg shows significant improvements of up to 56.5% in $F1$ score compared to the original SAM. In addition, RSAM-Seg maintains robust performance in few-shot learning scenarios, achieving an $F1$ score of 0.656 with only 1% of the training data and increasing to 0.815 with full data availability. Furthermore, RSAM-Seg exhibits the capability to detect missing areas within the ground truth of certain datasets, highlighting its capability for completion.

Clouds in remote sensing images inevitably affect information extraction, which hinders the following analysis of satellite images. Hence, cloud detection is a necessary preprocessing procedure. However, most existing methods have numerous calculations and parameters. In this paper, a lightweight CNN-Transformer network, CD-CTFM, is proposed to solve the problem, which is based on encoder-decoder architecture and incorporates the attention mechanism. In the encoder part, we utilize a lightweight network combing CNN and Transformer as backbone, which is conducive to extracting local and global features simultaneously. The backbone of CD-CTFM also incorporates attention gate based on dark channel extraction module. Moreover, a lightweight feature pyramid module is designed to fuse multiscale features with contextual information. In the decoder part, a lightweight channel-spatial attention module is integrated into each skip connection between encoder and decoder to extract low-level features while suppressing irrelevant information without introducing many parameters. Finally, the proposed model is evaluated on two cloud datasets, 38-Cloud and MODIS. The results demonstrate that CD-CTFM achieves comparable accuracy as the state-of-art methods and outperforms in terms of efficiency.

Piecewise linear regressions have shown many successful applications in image denoising, signal process, and data mining fields. In essence, they attempt to seek multiple linear functions (piecewise/stepwise function) to fit the given scatter data points by various methodologies, typically, pointcentered clustering methods such as k-means or FCM (Fuzzy c means). Obviously, it is reasonable that planecentered clustering is more suitable for capturing the linearities in data. In this paper, we propose an efficient Piecewise linear regression method based on k-Plane Clustering, termed as PlrPC. The proposed method firstly partitions the data into multiple plane-centered clusters and then analytically compute corresponding piecewise linear functions. Compared to the state-to-the-art linear regressors, the advantages of the PlrPC lie in 4-fold: 1) it generates from plane clustering, which is truly coincident with geometrical intuition; 2) to fuse the linear characteristics into plane clustering, a new implicit regression method is proposed; 3) a new plane jump method is proposed to detect the number of clusters; 4) the leading problem can be solved by ordinary eigenvalue problems. Experimental results will show the foresaid characters on some artificial and some benchmark datasets.

Clouds in satellite images limit the ability of imagery to extract the ground information, which makes it difficult to the following image analysis tasks. Hence, cloud detection is a changeling but fundamental task in the preprocessing of satellite image processing. In this letter, an encoder–decoder neural network architecture, cloud detection with ACON and attention mechanism (CAA)-UNet, is proposed for cloud detection. CAA-UNet is based on U-Net architecture and incorporates the attention mechanism. The asymmetric encoder and decoder blocks are proposed to discover more discriminative features. Then, a modified attention gate is integrated into each skip connection to highlight salient features. These make our model distinguish between the cloud and noncloud more accurately. Furthermore, the recent new and effective activate function, ActivateOrNot (ACON), is introduced into our model, which allows each neuron to adaptively activate or not, and improves the performance remarkably. Finally, the experiment results on two cloud datasets, Landsat-8 and a high-resolution cloud (HRC) cover validation dataset, show that CAA-UNet outperforms the state-of-the-art methods, especially in comprehensive indicators: Jaccard index, $F_{1}$ score, and overall accuracy.