Detecting small targets in infrared images presents significant challenges due to their tiny size and complex backgrounds, making this task a hotspot for research. Traditional methods rely on assumption-based modeling and manual design, struggling to handle the variability of real-world scenarios. Although convolutional neural networks (CNNs) increase robustness to diverse scenes with a data-driven paradigm, many CNN-based methods are insufficient in capturing fine-grained details necessary for small targets and are less effective during multi-scale feature fusion. To overcome these challenges, we propose the novel Wide-scale Gated Fully Fusion Network (WGFFNet) in this article, which contributes to infrared small-target detection (IRSTD). WGFFNet uses a classic encoder–decoder structure, where the designed stepped fusion block (SFB) embedded in the feature extraction stage captures finer local context across multiple scales during encoding, and along the decoding path, the multi-level features are progressively integrated by a Fully Gated Interaction (FGI) Module to enhance feature representation. The inclusion of a boundary difference loss further optimizes the edge details of targets. We conducted comprehensive experiments on two public infrared small-target datasets: SIRST-V2 and IRSTD-1k. Quantitative and qualitative results demonstrate that our WGFFNet outperforms representative methods when considering various evaluation metrics together, achieving an improved detection performance and computational efficiency for detecting small targets in infrared images.

Arable land is fundamental to agricultural production and a crucial component of ecosystems. However, its complex texture and distribution in remote sensing images make it susceptible to interference from other land cover types, such as water bodies, roads, and buildings, complicating accurate identification. Building on previous research, this study proposes an efficient and lightweight CNN-based network, U-MGA, to address the challenges of feature similarity between arable and non-arable areas, insufficient fine-grained feature extraction, and the underutilization of multi-scale information. Specifically, a Multi-Scale Adaptive Segmentation (MSAS) is designed during the feature extraction phase to provide multi-scale and multi-feature information, supporting the model’s feature reconstruction stage. In the reconstruction phase, the introduction of the Multi-Scale Contextual Module (MCM) and Group Aggregation Bridge (GAB) significantly enhances the efficiency and accuracy of multi-scale and fine-grained feature utilization. The experiments conducted on an arable land dataset based on GF-2 imagery and a publicly available dataset show that U-MGA outperforms mainstream networks (Unet, A2FPN, Segformer, FTUnetformer, DCSwin, and TransUnet) across six evaluation metrics (Overall Accuracy (OA), Precision, Recall, F1-score, Intersection-over-Union (IoU), and Kappa coefficient). Thus, this study provides an efficient and precise solution for the arable land recognition task, which is of significant importance for agricultural resource monitoring and ecological environmental protection.

Cultivated land is a vital resource that underpins human survival and sustainable social development. With the widespread use of high-resolution remote sensing imagery, conventional change detection methods often suffer from limited accuracy due to pseudo-changes and insufficient feature representation when dealing with complex land structures and significant seasonal variations. To address the challenges of representing multi-scale structures, mitigating pseudo-change interference, and accurately delineating boundaries in cultivated land change detection, this study proposes a diffusion-guided change detection network—FarmChanger. The network is designed based on the principles of adaptive feature extraction and diffusion-inspired feature refinement. These components are further integrated through cross-feature guidance to enhance spatial details, forming an end-to-end detection framework. Comprehensive evaluations on the CLCD and Peixian benchmark datasets demonstrate that FarmChanger achieves comparable or superior performance to mainstream models across multiple evaluation metrics, verifying its high accuracy and robustness in cultivated land dynamic monitoring tasks.

Multispectral LiDAR can simultaneously obtain distance and spectral information and shows great potential for underwater detection. However, absorption and scattering caused by suspended particles in water lead to energy attenuation and multiple scattering, which affect echo intensity and ranging accuracy, while the propagation characteristics under multi-wavelength conditions remain insufficiently studied. In this study, a simplified underwater propagation simulation model for multispectral LiDAR is established based on the equivalent spherical-particle assumption, combining Mie scattering theory with a semi-analytical Monte Carlo method. The effects of particle size on echo intensity and ranging error are analyzed under fixed concentration conditions. Based on this model, a detection-threshold-constrained optimal wavelength selection criterion is formulated. Multi-distance analysis (3, 5, 8, and 15 m) confirms that the preferred wavelength is primarily governed by particle size and remains stable across depths. The results show that the optimal detection wavelength shifts with particle size, being about 560 nm for fine particles and gradually moving toward the 400–480 nm blue–green band for larger particles. Experimental validation shows that the simulation-based ranging correction reduces RMSE by 9.4–25.9% (average 18.1%) and MAE by 11.8–29.7% (average 22.0%) across five experimental distances. The results provide a preliminary reference for wavelength selection in multispectral LiDAR systems under simplified conditions.

Forest fires occur frequently in China; however, the complex terrain and incomplete road networks severely constrain ground rescue efficiency. Accurate forest road information is essential for the optimization of emergency response and rescue force deployment. Existing road extraction algorithms are primarily designed for urban environments and exhibit limited efficacy in forest scenarios due to dense canopy, complex background interference and specific forest road features. To address this gap, this study proposes a forest road extraction method based on an enhanced DeepLabv3+ model using multi-temporal, high-resolution satellite imagery. Specifically, a Multi-Scale Channel Attention (MCSA) mechanism is embedded in skip connections to suppress background interference, while strip pooling is integrated into the Atrous Spatial Pyramid Pooling (ASPP) module to better capture slender road features. A composite Focal-Dice loss function is also constructed to mitigate sample imbalance. Finally, by applying the model in multi-temporal remote sensing images, a fusion strategy is introduced to integrate multi-seasonal road masks to enhance overall accuracy and topological integrity. Experimental results show that the proposed method achieves a precision of 54.1%, an F1-Score of 59.3%, and an IoU of 41.8%, effectively enhancing road continuity and providing robust technical support for fire-rescue decision-making.