Shadow detection is a basic task of remote sensing image analysis, but it is often seriously disturbed by vegetation, water bodies, and black objects. It is observed that vegetation and dark objects often show a dark look in visible bands but brighter in the near-infrared (NIR), and is also noticed that the reflection of inland water bodies in the green band is stronger than that in the blue band. Taking advantage of these physical properties and combining them with the bluish and dark appearance of shadows, we propose a simple but effective shadow detection method for multispectral remote sensing images. These physical properties are used to create transformation models that suppress features such as vegetation, water bodies, etc., but at the same time enhance shadows. Then, we transform the shadow representation into a color space to generate candidate shadows using dominant color components. To separate shadows from the others, we propose two indexes, the normalized Color Difference Composite Index (CDCI) and Color Purity Index (CPI), and fuse them to achieve shadows and their confidence. The experimental results indicate that the proposed method can effectively detect the shadows in multispectral images and outperforms the state-of-the-art approaches.

Recently, deep learning has shown great potential in areas such as infrared small target detection, but due to the lack of sample datasets, especially the public infrared small target dataset, model training, and extensive research have been limited. Synthetic data that contains a lot of information about the shape and scene of the target is widely used to augment real-world data. However, due to the domain shift between the real and synthetic data domains, combining them directly may not lead to significant improvements or even worse results. In this paper, we propose a semantic domain adaptive framework for cross-domain infrared small target detection (SDAISTD), which effectively decreases the domain shift between the real and synthetic data domains, leading to better training and detection results. Specially, SDAISTD uses a supervised learning adaptation approach from the feature perspective. The domain shift of cross-domain is diminished by extracting domain invariant features to align different feature distributions in the feature space. Additionally, we propose a semantic feature alignment loss function that effectively mitigates semantic information misalignment and aligns category features. Extensive experiments and analyses conducted on two baselines demonstrate the generality and validity of our proposed framework. Remarkably, our framework outperforms several representative baseline models in the new State-Of-The-Art records.

Convolutional neural networks have been widely used in remote sensing classification and achieved quite good results. Most of these methods are based on datasets with relatively balanced samples, but such ideal datasets are rare in applications. Long-tailed datasets are very common in practice, and the number of samples among categories in most datasets is often severely uneven and leads to bad results, especially in the category with a small sample number. To address this problem, a novel remote sensing image classification method based on loss reweighting for long-tailed data is proposed in this paper to improve the classification accuracy of samples from the tail categories. Firstly, abandoning the general weighting approach, the cumulative classification scores are proposed to construct category weights instead of the number of samples from each category. The cumulative classification score can effectively combine the number of samples and the difficulty of classification. Then, the imbalanced information of samples from each category contained in the relationships between the rows and columns of the cumulative classification score matrix is effectively extracted and used to construct the required classification weights for samples from different categories. Finally, the traditional cross-entropy loss function is improved and combined with the category weights generated in the previous step to construct a new loss reweighting mechanism for long-tailed data. Extensive experiments with different balance ratios are conducted on several public datasets, such as HistAerial, SIRI-WHU, NWPU-RESISC45, PatternNet, and AID, to verify the effectiveness of the proposed method. Compared with other similar methods, our method achieved higher classification accuracy and stronger robustness.

Infrared small target detection is crucial in military applications such as guidance, early warning, and UAV detection. Errors in infrared small target detection are classified as either miss detection (MD) or false alarm (FA). An effective detector should minimize both MD and FA. However, conventional approaches often rely on a single strategy to reduce overall detection errors, which can result in either MD or FA. To address this, we propose a dual-branch gate-aware network (DBGNet) model, that consists of two branches, each learning feature to reduce MD and FA, respectively. Specifically, a multi-scale full convolutional network (MFCN) is first applied to extract different level features to preserve the information of small infrared targets. Additionally, we introduce a multi-scale space and channel gate fusion module (MSCGFM) to ensure the independence of the two branches. Each branch is associated with its own learning objective loss function, enabling them to learn distinct discriminations while being constrained by the same category labels. Moreover, the features from both branches are fused to create a feature representation for each pixel in the image, addressing both MD and FA and minimizing MD while also reducing FA. Finally, the fused features from the two branches are passed through a classification head to generate prediction results. Extensive experimental results demonstrate that DBGNet outperforms other methods on three existing infrared small target datasets.

Insufficient sample is a common problem in hyperspectral image (HSI) classification and an important factor causing to low accuracy. Adding weak supervision mechanism to model training is an effective way to solve this problem. In this paper, we propose a weakly supervised HSI classification method with few samples based on intradomain sample expansion, which is anchored on the spatial correlation between samples. Firstly, to reduce the negative effects of spectral mixing on pseudolabel generation and classifier training, we introduce the continuous side window filter (SWF) to smooth the original hyperspectral images band by band. Second, in order to better balance the correctness and representativeness of the generated pseudolabels, a novel method for sample selection and pseudo-label generation is proposed in this paper. The method contains two branches, the segmentation graph based and the neighborhood relationship based. In the branch based on segmentation graphs, the polygon segmentation graph generated by the false color image is used to select the expansion samples. As a complementary branch, the branch based on neighborhood relationship exploits the neighborhood relationship and spectral similarity between samples to further select samples. Finally, in the classification stage, this paper uses the broad learning system as a classifier to obtain the classification graph. Experiments on three publicly available datasets show that the method in this paper can effectively achieve sample expansion and improve the classification accuracy and stability of hyperspectral images in the case of insufficient labeled samples.