Object detection has made tremendous progress in natural images over the last decade. However, the results are hardly satisfactory when the natural image object detection algorithm is directly applied to satellite images. This is due to the intrinsic differences in the scale and orientation of objects generated by the bird’s-eye perspective of satellite photographs. Moreover, the background of satellite images is complex and the object area is small; as a result, small objects tend to be missing due to the challenge of feature extraction. Dense objects overlap and occlusion also affects the detection performance. Although the self-attention mechanism was introduced to detect small objects, the computational complexity increased with the image’s resolution. We modified the general one-stage detector YOLOv5 to adapt the satellite images to resolve the above problems. First, new feature fusion layers and a prediction head are added from the shallow layer for small object detection for the first time because it can maximally preserve the feature information. Second, the original convolutional prediction heads are replaced with Swin Transformer Prediction Heads (SPHs) for the first time. SPH represents an advanced self-attention mechanism whose shifted window design can reduce the computational complexity to linearity. Finally, Normalization-based Attention Modules (NAMs) are integrated into YOLOv5 to improve attention performance in a normalized way. The improved YOLOv5 is termed SPH-YOLOv5. It is evaluated on the NWPU-VHR10 dataset and DOTA dataset, which are widely used for satellite image object detection evaluations. Compared with the basal YOLOv5, SPH-YOLOv5 improves the mean Average Precision (mAP) by 0.071 on the DOTA dataset.

A compact, static hyperspectral imaging linear polarimeter (HILP) based on a Savart interferometer (SI) is conceptually described. It improves the existing SI by replacing front polarizer with two Wollaston prisms, and can simultaneously acquire four interferograms corresponding to four linearly polarized lights on a single CCD. The spectral dependence of linear Stokes parameters can be recovered with Fourier transformation. Since there is no rotating or moving parts, the system is relatively robust. The interference model of the HILP is proved. The performance of the system is demonstrated through a numerical simulation, and the methods for compensating the imperfection of the polarization elements are described.

In the domain of Infrared Small Target Detection (IRSTD), the challenges revolve around detecting small and faint targets from infrared images. These targets lack distinct textures and morphology exist in complex backgrounds with numerous distractions. Current deep-learning methods typically prioritize preserving target features while neglecting the crucial background context, ultimately resulting in false alarms and miss detection. To tackle this issue, we propose a novel approach involving separately focusing on candidate target responses and background context during the encoding stage and aligning them during the decoding stage. Specifically, we introduce the Progressive Background-aware Transformer (PBT) which adopts an asymmetric encoder-decoder architecture. The encoder with task-specific frequency domain priors extracts candidate target responses and background context features separately from shallow and deep blocks, respectively. The following hierarchical decoder progressively refines the candidate target responses under the guidance of rich background context stage by stage, leading to more accurate results. Our experiments demonstrate that PBT surpasses state-of-the-art IRSTD methods across various datasets. The code and dataset are available at https://github.com/Heron0625/PBT.

Hyperspectral images are widely used for classification due to its rich spectral information along with spatial information. To process the high dimensionality and high nonlinearity of hyperspectral images, deep learning methods based on convolutional neural network (CNN) are widely used in hyperspectral classification applications. However, most CNN structures are stacked vertically in addition to using a onefold size of convolutional kernels or pooling layers, which cannot fully mine the multiscale information on the hyperspectral images. When such networks meet the practical challenge of a limited labeled hyperspectral image dataset—i.e., “small sample problem”—the classification accuracy and generalization ability would be limited. In this paper, to tackle the small sample problem, we apply the semantic segmentation function to the pixel-level hyperspectral classification due to their comparability. A lightweight, multiscale squeeze-and-excitation pyramid pooling network (MSPN) is proposed. It consists of a multiscale 3D CNN module, a squeezing and excitation module, and a pyramid pooling module with 2D CNN. Such a hybrid 2D-3D-CNN MSPN framework can learn and fuse deeper hierarchical spatial–spectral features with fewer training samples. The proposed MSPN was tested on three publicly available hyperspectral classification datasets: Indian Pine, Salinas, and Pavia University. Using 5%, 0.5%, and 0.5% training samples of the three datasets, the classification accuracies of the MSPN were 96.09%, 97%, and 96.56%, respectively. In addition, we also selected the latest dataset with higher spatial resolution, named WHU-Hi-LongKou, as the challenge object. Using only 0.1% of the training samples, we could achieve a 97.31% classification accuracy, which is far superior to the state-of-the-art hyperspectral classification methods.

Change detection (CD) aims to identify differences in scenes observed at different times. Hyperspectral image (HSI) is preferred for the understanding of land surface changes, since it can provide essential and unique features for CD. However, due to the high-dimensionality and limited data, the HSI-CD task is challenged. While model-driven CD methods are hard to achieve high accuracy due to the weak detection performance for fine changes, data-driven CD methods are hard to be generalized due to the limited datasets. The state-of-art method is to combine a single model-driven method with a data-driven convolutional neural network (CNN). Wherein the pseudolabels can be generated automatically by the model-driven method and then fed to CNN for training. However, the final detection accuracy is limited by the model-driven method which produces pseudolabels with one-sidedness and low accuracy. Therefore, the generation of credible pseudolabels is anticipated and crucial for such a combination. Herein, a novel strategy, the combination of two complementary model-driven methods, structural similarity (SSIM) and change vector analysis (CVA), is proposed to generate credible labels for training a subsequent CNN. The results show that the final accuracy is higher than that of SSIM and CVA. The main contributions of this article are threefold: First, a new paradigm for generating credible labels is proposed. Second, SSIM is used for the first time for HSI-CD tasks. Third, an unsupervised end-to-end framework is presented for the HSI-CD. Experimental results demonstrate the effectiveness of the proposed framework.

Single-snapshot full-Stokes imaging polarimetry is a powerful tool for the acquisition of the spatial polarization information in real time. According to the general linear model of a polarimeter, to recover full Stokes parameters at least four polarimetric intensities should be measured. In this paper, four types of single-snapshot full-Stokes division-of-aperture imaging polarimeter with four subapertures are presented and compared, with maximum spatial resolution for each polarimetric image on a single area-array detector. By using the error propagation theories for different incident states of polarization, the performance of four polarimeters are evaluated for several main sources of error, including retardance error, alignment error of retarders, and noise perturbation. The results show that the configuration of four 132° retarders with angular positions of ( ± 51.7°, ± 15.1°) is an optimal choice for the configuration of four subaperture single-snapshot full-Stokes imaging polarimeter. The tolerance and uncertainty of this configuration are analyzed.