The fusion of hyperspectral imagery (HSI) and light detection and ranging (LiDAR) data for classification has received widespread attention and has led to significant progress in research and remote sensing applications. However, existing common CNN architectures suffer from the significant drawback of not being able to model remote sensing images globally, while transformer architectures are not able to capture local features effectively. To address these bottlenecks, this paper proposes a classification framework for multisource remote sensing image fusion. First, a spatial and spectral feature projection network is constructed based on parallel feature extraction by combining HSI and LiDAR data, which is conducive to extracting joint spatial, spectral, and elevation features from different source data. Furthermore, in order to construct local–global nonlinear feature mapping more flexibly, a network architecture coupling together multiscale convolution and a multiscale vision transformer is proposed. Moreover, a plug-and-play nonlocal feature token aggregation module is designed to adaptively adjust the domain offsets between different features, while a class token is employed to reduce the complexity of high-dimensional feature fusion. On three open-source remote sensing datasets, the performance of the proposed multisource fusion classification framework improves about 1% to 3% over other state-of-the-art algorithms.

Recent advancements in space exploration technology have significantly increased the number of diverse satellites in orbit. This surge in space-related information has posed considerable challenges in developing space target surveillance and situational awareness systems. However, existing detection algorithms face obstacles such as complex space backgrounds, varying illumination conditions, and diverse target sizes. To address these challenges, we propose an innovative end-to-end Attention-Guided Encoder DETR (AgeDETR) model, since artificial intelligence technology has progressed swiftly in recent years. Specifically, AgeDETR integrates Efficient Multi-Scale Attention (EMA) Enhanced FasterNet block (EF-Block) within a ResNet18 (EF-ResNet18) backbone. This integration enhances feature extraction and computational efficiency, providing a robust foundation for accurately identifying space targets. Additionally, we introduce the Attention-Guided Feature Enhancement (AGFE) module, which leverages self-attention and channel attention mechanisms to effectively extract and reinforce salient target features. Furthermore, the Attention-Guided Feature Fusion (AGFF) module optimizes multi-scale feature integration and produces highly expressive feature representations, which significantly improves recognition accuracy. The proposed AgeDETR framework achieves outstanding performance metrics, i.e., $97.9\%$ in ${mAP}_{0.5}$ and $85.2\%$ in $mA{P}_{0.5:0.95}$, on the SPARK2022 dataset, outperforming existing detectors and demonstrating superior performance in space target detection.

Gathering extensive labeled data during Mars missions is costly and unrealistic, especially considering the complex and unpredictable Martian environment where new and unfamiliar scenes may emerge. Traditional Mars scene classification methods depend heavily on large amounts of labeled data, which makes it impractical to recognize previously unseen scene classes without the necessary labeled examples. Additionally, the significant computational demands and parameter requirements of modern models also pose challenges for their integration into resource-constrained systems used in Mars exploration. To address these issues, we propose a zero-shot Mars scene classification framework, which is able to categorize unseen Martian image scenes without the prior acquisition of vast visual examples. Specifically, the framework combines lightweight model design with knowledge distillation techniques, known as KDMSC, to streamline complex zero-shot learning models. It employs a knowledge distillation loss that captures essential knowledge through the training of the teacher model from scratch, thereby improving the zero-shot classification performance of the student model. Consequently, the lightweight student model is tailored for deployment on devices with limited resources while fulfilling the requirements of the zero-shot Mars scene classification tasks. Moreover, to support the zero-shot Mars scene classification initiative, we developed a dataset named ZSMars to further advance this field. Experimental results indicate that our model excels in the zero-shot Mars scene classification tasks while maintaining low computational complexity and storage requirements.

Small target detection has become an important part of space exploration missions. The existence of weak illumination and interference from the background of star charts in deep and distant space has brought great challenges to space target detection. In addition, the distance of space targets is usually far, so most of them are small targets in the image, and the detection of small targets is also very difficult. To solve the above problems, we propose a multi-scale feature fusion pyramid network. First, we propose the CST module of a CNN fused with Swin Transformer as the feature extraction module of the feature pyramid network to enhance the extraction of target features. Then, we improve the SE attention mechanism and construct the CSE module to find the attention region in the dense star map background. Finally, we introduce improved spatial pyramid pooling to fuse more features to increase the sensory field to obtain multi-scale object information and improve detection performance for small targets. We provide two versions and conducted a detailed ablation study to empirically validate the effectiveness and efficiency of the design of each component in our network architecture. The experimental results show that our network improved in performance compared to the existing feature pyramid.

Zero-shot classification models aim to recognize image categories that are not included in the training phase by learning seen scenes with semantic information. This approach is particularly useful in remote sensing since it can identify previously unseen classes. However, most zero-shot remote sensing scene classification approaches focus on matching visual and semantic features, while disregarding the importance of visual feature extraction, especially regarding local-global joint information. Furthermore, the visual and semantic relationships have not been thoroughly investigated due to the separate analysis of these features. To address these issues, we propose a novel zero-shot remote sensing scene classification network based on multimodal feature interaction (MFINet). Specifically, the MFINet deploys hybrid image feature extraction networks, combining convolutional neural networks and an improved Transformer, to capture local discriminant information and long-range contextual information, respectively. Notably, we design a cross-modal feature fusion (CMFF) module to facilitate the multimodal feature interaction, thereby enhancing relevant information in both the visual and semantic domains. Extensive experiments are conducted on the public zero-shot remote sensing scene dataset, and the results consistently demonstrate that our proposed MFINet outperforms the state-of-the-art methods across various seen/unseen category ratios.

Current hyperspectral image (HSI) reconstruction methods primarily rely on image-level approaches, which are time-consuming to form abundant high-quality HSIs through imagers. In contrast, spectrometers offer a more efficient alternative by capturing high-fidelity point spectra, enabling pixel-level HSI reconstruction that balances accuracy and label efficiency. To this end, we introduce a pixel-level spectral super-resolution (Pixel-SSR) paradigm that reconstructs HSI from RGB and point spectra. Despite its advantages, Pixel-SSR presents two key challenges: 1) generalizability to novel scenes lacking point spectra, and 2) effective information extraction to promote reconstruction accuracy. To address the first challenge, a Gamma-modeled strategy is investigated to synthesize point spectra based on their intrinsic properties, including nonnegativity, a skewed distribution, and a positive correlation. Furthermore, complementary three-branch prompts from RGB and point spectra are extracted with a Dynamic Prompt Mamba (DyPro-Mamba), which progressively directs the reconstruction with global spatial distributions, edge details, and spectral dependency. Comprehensive evaluations, including horizontal comparisons with leading methods and vertical assessments across unsupervised and image-level supervised paradigms, demonstrate that ours achieves competitive reconstruction accuracy with efficient label consumption.